Skip to content

[ROCm][CI] Gate incompatible HF references on Transformers v5#41532

Merged
DarkLight1337 merged 17 commits into
vllm-project:mainfrom
ROCm:akaratza_lang_mod_hf
Jun 16, 2026
Merged

[ROCm][CI] Gate incompatible HF references on Transformers v5#41532
DarkLight1337 merged 17 commits into
vllm-project:mainfrom
ROCm:akaratza_lang_mod_hf

Conversation

@AndreasKaratzas

@AndreasKaratzas AndreasKaratzas commented May 3, 2026

Copy link
Copy Markdown
Member

This updates generation-test metadata for models whose HF reference path is incompatible with the installed Transformers v5 runtime.

Test groups fixed:

  • mi355_1: Language Models Tests (Standard) for MiniCPM4.
  • mi355_1: Language Models Test (Extended Generation) for HyperCLOVAX.

MiniCPM4:

HyperCLOVAX:

  • The model's remote code imports ROPE_INIT_FUNCTIONS and unconditionally indexes ROPE_INIT_FUNCTIONS[self.rope_type]; for the default case, self.rope_type is "default": https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-14B/blob/main/modeling_hyperclovax.py
  • Transformers v5 docs still list "default" as a valid RoPE type. The incompatibility is narrower: v5 no longer exposes a "default" entry in ROPE_INIT_FUNCTIONS, while v4.57 did. In v5's own Llama code, default RoPE is handled by compute_default_rope_parameters; ROPE_INIT_FUNCTIONS is consulted only when rope_type != "default".
  • The v5 migration guide also notes that rotary embedding configuration now lives under config.rope_parameters, which matches the new v5 model path.

cc @kenroche

@AndreasKaratzas
[ROCm][CI] Gate incompatible HF references on Transformers v5
009c271 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
@AndreasKaratzas AndreasKaratzas marked this pull request as ready for review May 3, 2026 04:15
claude[bot]
claude Bot reviewed May 3, 2026
View reviewed changes

@claude claude Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Claude Code Review

This pull request is from a fork — automated review is disabled. A repository maintainer can comment @claude review to run a one-time review.

@AndreasKaratzas AndreasKaratzas added the rocm Related to AMD ROCm label May 3, 2026
@github-project-automation github-project-automation Bot moved this to Todo in AMD May 3, 2026
gemini-code-assist[bot]
gemini-code-assist Bot reviewed May 3, 2026
View reviewed changes

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the model testing framework to include model revisions and trust_remote_code flags. It also introduces version constraints for specific models in the registry. Feedback was provided regarding a logic bug where adding a version reason causes tests to be skipped regardless of version validity, and a concern that the specified Transformers version range for MiniCPM4 appears to be incorrect or overly restrictive.

Comment thread tests/models/registry.py Outdated
Comment thread tests/models/registry.py
@AndreasKaratzas
[Bugfix] Fix transformers version reason gating logic
aa01552 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This was referenced May 4, 2026
Closed
Closed
@AndreasKaratzas

AndreasKaratzas commented May 4, 2026

Copy link
Copy Markdown
Member Author

cc @charlifu

@tjtanaa tjtanaa added the ready ONLY add when PR is ready to merge/full CI is needed label May 4, 2026
@mergify mergify Bot added the multi-modality Related to multi-modality (#4194) label May 5, 2026
@AndreasKaratzas

AndreasKaratzas commented May 5, 2026

Copy link
Copy Markdown
Member Author

Notes on the AudioFlamingo3 / MusicFlamingo changes:

  • Transformers 5.5 native processors now require a 1:1 mapping between text entries and audio entries. vLLM's processor path supports multiple audio items inside one prompt, so the AudioFlamingo3 multimodal processor now performs the HF processor's windowing, feature extraction, prompt expansion, and tokenization locally for this single-prompt multi-audio case.
  • MusicFlamingo's native processor no longer returns rote_timestamps. vLLM now derives the same rotary-time timestamps from chunk_counts and the encoded audio sequence length inside the model path, while still accepting rote_timestamps if an older processor provides them.
  • MusicFlamingo prompt expansion now includes the audio BOS/EOS tokens expected by its prompt replacement metadata.
  • transformers_version_reason now only applies when the installed version misses the configured min/max bound. This keeps the AudioFlamingo3/MusicFlamingo "Needs PR 43538" explanation for versions below 5.3.0 without skipping supported 5.5.3 runs.

hmellor

This comment was marked as outdated.

Sign in to view

@hmellor hmellor dismissed their stale review May 6, 2026 14:52

misunderstanding

eustlb
eustlb reviewed May 20, 2026
View reviewed changes

@eustlb eustlb left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

transformers releases
AudioFlamingo3: v5.0.0
MusicFlamingo3: v5.5.0

There should not be any reasons not to use super()._call_hf_processor. Looks like a lot of the confusion here comes from the fact that the vLLM PR was merged before the transformers one on which it depended, and that evolved after the vLLM one was merged.

Such fixes should be addressed in work already started in #39011, but happy to help if needed. @lashahub looping you in here

@AndreasKaratzas
Merge remote-tracking branch 'origin/main' into akaratza_lang_mod_hf
0307fc6 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
@AndreasKaratzas
[CI] Fix Flamingo3 HF processor alignment and MusicFlamingo audio pre…
37e7865 
…processing

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
@AndreasKaratzas

AndreasKaratzas commented May 21, 2026

Copy link
Copy Markdown
Member Author

I pushed some more changes (a lot of them actually). The main intent is to stop carrying vLLM-local copies of preprocessing that now belongs to the upstream HF processors. So vLLM had manual chunking, feature extraction, and audio-token expansion logic. With AudioFlamingo3 at transformers v5.0.0 and MusicFlamingo at v5.5.0, that logic should live in HF, while vLLM keeps only the adapter bookkeeping needed for batching, placeholder matching, and model execution.

In audioflamingo3.py, _call_hf_processor now calls super()._call_hf_processor(...). The deleted active-path code was duplicating HF behavior: manually splitting audio into chunks, calling the feature extractor directly, normalizing masks, expanding <sound> tokens, then calling the tokenizer. Current HF AudioFlamingo3Processor.__call__ already does those pieces.

The remaining vLLM logic after super() is:

  • Copy mm_data first so we do not mutate the caller's mapping with pop.
  • Map vLLM's "audios" alias to HF's "audio" argument.
  • Rename HF's input_features_mask to vLLM's feature_attention_mask.
  • Compute chunk_counts, because HF returns flattened audio chunks but vLLM still needs to regroup chunk embeddings back per original audio item.

So chunk_counts is not a replacement for HF preprocessing. It is vLLM batching metadata.

I also removed MusicFlamingo's _call_hf_processor because after the AudioFlamingo3 parent method was fixed, the MusicFlamingo override only duplicated parent behavior and recomputed chunk_counts. MusicFlamingo can inherit the shared AudioFlamingo3 adapter path.

Also regarding MusicFlamingo's _expand_audio_tokens, I think that current HF MusicFlamingoProcessor expands audio placeholders itself, including the MusicFlamingo-specific BOS/audio/EOS pattern. Keeping a second vLLM implementation risks drifting from HF again. vLLM still keeps MusicFlamingo prompt replacement in musicflamingo.py, because vLLM needs to match generated placeholder token IDs to multimodal embedding slots.

The partial_rotary_factor change in musicflamingo.py aligns with current transformers. The previous code used the full head dimension. HF computes dim = int(head_dim * partial_rotary_factor), so I think that vLLM was rotating the wrong dimensionality.

The RoPE forward change from flattened batch_positions to timestamp-derived window_positions also matches current HF. The old implementation made the rotary window axis depend on flattened chunk order. Current HF uses the actual window start timestamp, computes the audio window duration, then derives the window position from that. That matters for chunked audio and for matching single vs batched behavior.

The fp32 RoPE buffer restoration is there because vLLM model dtype/device application can cast non-persistent buffers to bf16. In the HF construction path we compare against, inv_freq and position_angles are built from torch.float, so they remain fp32 under the tested bf16 load path. These buffers feed trig functions; bf16 there is enough to create exact-output drift. _apply lets the module move to the right device, then recreates those RoPE buffers in fp32 on that device.

The cast in _encode_audio_features fixes the ROCm failure where processor output is fp32 but the audio tower conv weights/bias are bf16. ROCm/PyTorch requires input and bias dtypes to match for that conv path. Casting at model ingress is the right boundary: HF processors naturally produce float features, while the vLLM model owns execution dtype/device.

Also, for ROCm, the transcription was wrong yielding a weird "four-on-the-floor" with MusicFlamingo. Direct HF generation matched the original fixture, while vLLM's URL audio path produced a different transcription. The root cause was audio resampling: HF/librosa uses soxr-style resampling, while vLLM was using the default parser resampler. Switching only MusicFlamingo's parser to audio_resample_method="soxr" makes the input features match HF more closely without changing the global default for other models.

The MusicFlamingo generation test no longer skips missing fixtures because missing committed fixtures should be a test error, not a skip. The small warmup in test_musicflamingo.py is there because MI300/ROCm showed a first-inference exact-output drift during decoder kernel compilation; after a one-token warmup, the steady-state deterministic output matches.

cc @eustlb @hmellor Lmk what you guys think.

@mergify

mergify Bot commented May 21, 2026

Copy link
Copy Markdown
Contributor

Hi @AndreasKaratzas, the pre-commit checks have failed. Please run:

uv pip install pre-commit>=4.5.1
pre-commit install
pre-commit run --all-files

Then, commit the changes and push to your branch.

For future commits, pre-commit will run automatically on changed files before each commit.

Tip

Is mypy failing?
mypy is run differently in CI. If the failure is related to this check, please use the following command to run it locally: 
# For mypy (substitute "3.10" with the failing version if needed)
pre-commit run --hook-stage manual mypy-3.10

@lashahub

lashahub commented May 22, 2026

Copy link
Copy Markdown
Contributor

Thanks for looping me in.

AF-Next should not be added as a separate vLLM architecture anymore. The current HF checkpoints use the existing MusicFlamingo architecture (model_type=musicflamingo, MusicFlamingoForConditionalGeneration).

I’ll wait for this PR to settle/land, then rebase #39011 on top and re-scope it to AF-Next checkpoint coverage through MusicFlamingo only. That should avoid duplicating the Flamingo processor/RoTE fixes here.

@mergify

mergify Bot commented May 29, 2026

Copy link
Copy Markdown
Contributor

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @AndreasKaratzas.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify Bot added the needs-rebase label May 29, 2026
@AndreasKaratzas
Merge remote-tracking branch 'origin/main' into akaratza_lang_mod_hf
2a48a98 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
@AndreasKaratzas AndreasKaratzas requested a review from khluu as a code owner June 1, 2026 08:06
@mergify mergify Bot removed the needs-rebase label Jun 1, 2026
hmellor
hmellor approved these changes Jun 3, 2026
View reviewed changes

@hmellor hmellor left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This LGTM, I'd like @eustlb to have one last look at the audio code before we press the big green button though

@AndreasKaratzas

AndreasKaratzas commented Jun 4, 2026

Copy link
Copy Markdown
Member Author

Hi @eustlb, could you please confirm?

@lashahub lashahub mentioned this pull request Jun 11, 2026
Closed
5 tasks
@Vedant-Agarwal Vedant-Agarwal mentioned this pull request Jun 11, 2026
Closed
@AndreasKaratzas

AndreasKaratzas commented Jun 12, 2026

Copy link
Copy Markdown
Member Author

cc @eustlb PTAL

eustlb
eustlb approved these changes Jun 16, 2026
View reviewed changes

@eustlb eustlb left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM on the calls to transformers' processors for the audio part (audioflamingo + musicflaming) 👍

@DarkLight1337 DarkLight1337 merged commit 7e179e4 into vllm-project:main Jun 16, 2026
179 of 180 checks passed
@github-project-automation github-project-automation Bot moved this from Todo to Done in AMD Jun 16, 2026
@AndreasKaratzas AndreasKaratzas deleted the akaratza_lang_mod_hf branch June 16, 2026 15:53
vivek8123 pushed a commit to odh-on-pz/vllm-upstream that referenced this pull request Jun 18, 2026
@AndreasKaratzas
[ROCm][CI] Gate incompatible HF references on Transformers v5 (vllm-p…
c69325b 
…roject#41532)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: vivek sharma <vivsharm@redhat.com>
@okorzh-amd okorzh-amd mentioned this pull request Jun 18, 2026
Merged
4 tasks
divineearthly pushed a commit to divineearthly/vllm that referenced this pull request Jun 19, 2026
@AndreasKaratzas @divineearthly
[ROCm][CI] Gate incompatible HF references on Transformers v5 (vllm-p…
82aef90 
…roject#41532)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: divineearthly <divineearthly@gmail.com>
xuebwang-amd pushed a commit to xuebwang-amd/vllm that referenced this pull request Jun 21, 2026
@AndreasKaratzas @xuebwang-amd
[ROCm][CI] Gate incompatible HF references on Transformers v5 (vllm-p…
fae8844 
…roject#41532)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
tunglinwood pushed a commit to tunglinwood/vllm that referenced this pull request Jun 22, 2026
@AndreasKaratzas
[ROCm][CI] Gate incompatible HF references on Transformers v5 (vllm-p…
daa7cbc 
…roject#41532)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
lcheng321 pushed a commit to lcheng321/vllm that referenced this pull request Jun 22, 2026
@AndreasKaratzas @lcheng321
[ROCm][CI] Gate incompatible HF references on Transformers v5 (vllm-p…
f1c9bba 
…roject#41532)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: lcheng <lcheng321@gatech.edu>
RhizoNymph added a commit to RhizoNymph/vllm that referenced this pull request Jun 22, 2026
@RhizoNymph @xiaohongchen1991
@gmagogsfm @mergify @wentian-byte @ricky-chaoju @BugenZhao @bbrowning @xianbaoqian @claude @yewentao256 @yzong-rh @Dao007forever @nascheme @jjppp @littlecircle0730 @orozery @Fangzhou-Ai @Sunt-ing @njhill @sasindharan @chaunceyjiang @ekagra-ranjan @varun-sundar-rabindranath @cleonard530 @divakar-amd @LucasWilkinson @martin-kukla @MatthewBonanni @NickLucche @jiahanc @aleckohlhoff @porrashuang @scoootscooob @Isotr0py @Rohan138 @yuwenzho @wseaton @majian4work @mgoin @cjackal @xiaguan @fynnsu @jperezdealgaba @tdoublep @Harry-Chen @snadampal @zhenwei-intel @jikunshang @chfeng-cs @thillai-c @markmc @guan404ming @Srinivasoo7 @sridhar-3009 @tahsintunan @vincentzed @j-i-l @zixi-qi @zyongye @rjrock @gemini-code-assist @sfeng33 @micah-wil @khluu @waynehacking8 @abinggo @ywang96 @AndreasKaratzas @hickeyma @anony-mous-e @hmellor @Achyuthan-S @xinli-sw @ShawRong @Change72 @benchislett @majunze2001 @mfylcek @amd-asalykov @mrn3088 @taneem-ibrahim @noa-neria @chaojun-zhang @maobaolong @bigPYJ1151 @panpan0000 @sahilsGit @TheEpicDolphin @FAUST-BENCHOU @reidliu41 @Yejing-Lai @vllmellm @noooop @xin3he @mikekg @mikekgfb @Saddss @ZiguanWang @youkaichao @codex @gau-nernst @jeejeelee @functionstackx @ronensc @WoosukKwon @factnn @llx-08 @ZJY0516 @itayalroy @xx-thomas @lucianommartins @gitbisector @DarkLight1337 @Bortlesboat @thisisjimmyfb @JOSH1024 @wendyliu235 @zxd1997066 @wangxiyuan @shen-shanshan @HanHan009527 @amd-lalithnc @tlrmchlsmth @netanel-haber @fuscof-ibm @AjAnubolu @carlyou @tuukkjs @abcd1927 @CienetStingLin @kouroshHakha @alexbi29 @jesse996 @hongxiayang @m4r1k @mmangkad @s3woz @sungsooha @andakai @cquil11 @tjtanaa @nehmathe2 @liangel-02 @ovidiusm @hello-args @Etelis @EtelisIBM @j9smith @nikhilesh-csa @ruocco @oguzhankir @yiliu30 @n1ck-guo @Zhenzhong1 @xaguilar-amd @amirkl94 @ZhanqiuHu @danisereb @qli88 @wangjiaxin99 @dllehr-amd @shanjiaz @Oseltamivir @alexeldeib @jonathanc-n @Alex-ai-future
Integrate upstream/main into feat/integration (#186)
e0ca868 
* [Kernel][Helion][1/N] Add Helion kernel for per_token_group_fp8_quant (#36902)

Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Bugfix] Restrict FlashInfer cuDNN FP8 ViT attention gate to Blackwell (SM 100) (#45251)

Signed-off-by: Wentian Byte <3400259131@qq.com>

* [Rust Frontend] Support continuous_usage_stats stream option (#43965)

Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: RickyChen / 陳昭儒 <ricky.chen@infinirc.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>

* [Bugfix] Fix Anthropic tool_use content handling dropping args (#45287)

Signed-off-by: Ben Browning <bbrownin@redhat.com>

* [Model] Remove InternLMForCausalLM registry alias (#45128)

Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

* [Bug] Fix test flashmla for DSv4 (#45052)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* [Refactor] Chat Completions Harmony Refactor, non-streaming path. (#45171)

Signed-off-by: Yifan Zong <yzong@redhat.com>

* [Bugfix][KVConnector][Mooncake] Close MooncakeDistributedStore on connector teardown (#45206)

Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

* Make mistral_common optional by deferring MistralToolCall import (#45305)

Signed-off-by: Neil Schemenauer <nas@arctrix.com>

* [Bugfix] Initialize missing attributes in mistral eagle (#45217)

Signed-off-by: jpwang <jpwang@smail.nju.edu.cn>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Refactor] Chat Completions Streaming Harmony Refactor and Bugfixes (#45104)

Signed-off-by: Yifan Zong <yzong@redhat.com>

* [Bugfix] OffloadingConnector: respect skip_reading_prefix_cache flag (#44592)

Signed-off-by: Hsiao-Yuan Chen <hy.c@Hsiao-YuandeMacBook-Pro.local>
Signed-off-by: littlecircle0730 <littlecircle0730@gmail.com>
Signed-off-by: littlecircle0730 <43994952+littlecircle0730@users.noreply.github.com>
Co-authored-by: Hsiao-Yuan Chen <hy.c@Hsiao-YuandeMacBook-Pro.local>
Co-authored-by: Or Ozeri <or@ozery.com>

* [ROCm][DSv4][Perf] Flash-decode split-K decode attention kernel (#44899)

Co-authored-by: vLLM Contributor <contributor@vllm.ai>

* [Bugfix][Model] Pass revision by name in Run:ai and bitsandbytes index downloads (#45308)

Signed-off-by: Ting Sun <suntcrick@gmail.com>

* [CI][BugFix] Fix broken `test_mamba_prefix_cache.py` due to stale mock (#45345)

Signed-off-by: Nick Hill <nickhill123@gmail.com>

* [Bugfix] Fix --enable-prompt-tokens-details omitting zero cached tokens (#44383)

Signed-off-by: Sasindharan Sankar <sasindharansankar@email.com>
Co-authored-by: Sasindharan Sankar <sasindharansankar@email.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>

* [ASR] Optimize CPU preproc to get 2.5x RTFx via multi-threading (#44612)

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Bugfix] Mamba CPU Offloading (#44599)

Signed-off-by: varun sundar rabindranath <vsundarr@redhat.com>
Co-authored-by: varun sundar rabindranath <vsundarr@redhat.com>

* [ASR] Add Long Audio benchmark and correctness test (#44587)

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>

* [11a/n]  Migrate Marlin kernels to torch stable ABI (#45176)

Signed-off-by: Chris Leonard <chleonar@redhat.com>

* [NIXL] Per-region KV transfer classification for mixed full-attn + MLA groups (#44583)

* [ROCm][CI] fix fp8 support for test_deepep_moe (#45302)

Signed-off-by: Divakar Verma <divakar.verma@amd.com>

* [Model] Add DiffusionGemma Support (#45163)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Martin Kukla <martin.kukla@cantab.net>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Dipika Sikka <dsikka@redhat.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Alec Kohlhoff <134344302+aleckohlhoff@users.noreply.github.com>
Co-authored-by: Porras Huang <20535584+porrashuang@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: scoootscooob <167050519+scoootscooob@users.noreply.github.com>

* [MM][Perf][CG] Support ViT full cudagraphs for mllama4 (#40660)

Signed-off-by: allgather <all2allops@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

* [ROCm][gpt-oss] Pass GateMode.INTERLEAVE for MXFP4 W4A16 fused MoE (#44893)

Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>

* [Bugfix] Fix Dockerfile dependency graph pre-commit error (#45374)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

* [CPU] Support CPU W4A16 INT4 MoE (#43409)

Signed-off-by: yuwenzho <yuwen.zhou@intel.com>

* [Rust Frontend][Bugfix] Forward --shutdown-timeout and --disable-log-stats to the managed Python engine (#45300)

Signed-off-by: Will Eaton <weaton@redhat.com>

* [XPU][DeepSeek-V4] Fix MTP: sync with upstream fixes #44821 and #43746 (#45240)

Signed-off-by: Ma Jian <jian1.ma@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [CI] ci-fetch-log.sh: fetch all failed jobs from a build URL or PR number (#45274)

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

* [Frontend]  Support strict mode for tool calling (#45003)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: cjackal <44624812+cjackal@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Bugfix][Rust Frontend] Return 400 for prompt-validation submit errors (#45286)

Signed-off-by: xiaguan <751080330@qq.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

* Update hidden states extraction integration test triggers (#45294)

Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>

* Fix misleading error for audio duration limit rejection (#45113)

Signed-off-by: jperezde <jperezde@redhat.com>

* [Doc] AGENTS.md: add section about coding style (#45301)

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>

* [11b/n] Migrate Machete kernels to torch stable ABI (#45304)

Signed-off-by: Chris Leonard <chleonar@redhat.com>
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>

* [KV Connector]: Support KV push from Prefill to Decode node using Nixl KV Connector (#35264)

Signed-off-by: Sunita Nadampalli <nadampal@amazon.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

* [Model] Remove Mono-InternVL (InternLM2VEForCausalLM) (#45129)

Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

* [BUGFIX][XPU] Update fa interface for compatibility (#45394)

Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

* [Metrics] Add group-aware KV cache capacity to vllm:cache_config_info (#42206)

The startup log already reports the correct group-aware KV cache capacity for
hybrid models, but Prometheus did not expose matching info in 'vllm:cache_config_info`.

This PR adds kv_cache_size_tokens and kv_cache_max_concurrency.

Signed-off-by: Ethan Feng <ethan.fengch@gmail.com>

* [V1][Metrics] Add MLA attention metrics for DeepSeek MFU estimation (#39457)

Signed-off-by: Thillai Chithambaram <thillaichithambaram.a@gmail.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>

* [Bug] Migrate Reset cache for both v2 and v1 model runner (#42759)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Core] Support structured outputs for beam search (#35022)

Signed-off-by: Guan-Ming (Wesley) Chiu <guanmingchiu@gmail.com>
Signed-off-by: Guan-Ming (Wesley) Chiu <105915352+guan404ming@users.noreply.github.com>

* [Core][KV Connector] fix scheduler KV connector stats aggregation (#43877)

Fixes scheduler-side KV connector stats collection so that:

1. update_connector_output() runs before scheduler-side stats are collected.
2. worker-side and scheduler-side KV connector stats are aggregated when both are present.
3. scheduler-only KV connector stats are still emitted when no worker-side stats exist.

Signed-off-by: srinivas_oo7 <sklinkedin0120@gmail.com>
Co-authored-by: srinivas_oo7 <sklinkedin0120@gmail.com>

* [Frontend] Support strict mode for tool calling with ResponsesAPI (#45396)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>

* [Docs][KV Connector][NIXL] document KV Transfer stat logging and Prometheus metrics (#44055)

Signed-off-by: Sai Sridhar <tarrasridhar1154@gmail.com>

* [Rust Frontend] Add standalone `granite4` tool parser (#45216)

Signed-off-by: Tahsin Tunan <tahsintunan@gmail.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Model] Add encoder CUDA graph support to Lfm2VL (#44930)

Signed-off-by: vincentzed <207368749+vincentzed@users.noreply.github.com>

* [Kernel][Helion][1/N] Add Helion kernel for dynamic_per_token_scaled_fp8_quant (#33790)

Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>

* [Model][Dflash] Enable Dflash support for Qwen3NextForCausalLM targets (#45319)

Signed-off-by: Jonas I. Liechti <j-i-l@t4d.ch>

* [Migration] Migrate GGUF quantization support to plugin (#39612)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

* [Perf] Use native DSA indexer decode path for next_n > 2 on SM100 (#45322)

Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

* [Core][AMD] Propagate shutdown timeout to MultiprocExecutor (#43154)

Signed-off-by: Ryan Rock <ryan.rock@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* [Refactor] Deprecate ResponsesParser wrapper, inline parsing into ParsableContext (#45431)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

* [ROCm] Bump Torch to 2.11 (#45362)

Signed-off-by: Micah Williamson <micah.williamson@amd.com>

* [Attention] Improve attention benchmarks: configs and profiling (#39336)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>

* [Model Runner v2] Migration from v1 to v2, with Qwen and DSv2 MOE models [3/N] (#42667)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Kernel] Consolidate Marlin thread-tile padding across all dense Marlin paths (#45295)

Signed-off-by: mgoin <mgoin64@gmail.com>

* Add the QuantizedActivation linear-kernel contract (#44260)

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

* [ROCm][DSV4][Perf] Fuse inverse-RoPE and cache bf16 wo_a in o-projection (#45103)

Signed-off-by: Fangzhou Ai <fangzhouai@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

* [Bugfix][CPU] Don't build triton-cpu on arm64 release image (#45401)

Signed-off-by: khluu <khluu000@gmail.com>

* [BugFix] Avoid prematurely freeing cached mm encoder outputs (#45347)

Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Nick Hill <nickhill123@gmail.com>

* [Bugfix] Set type/role explicitly in streaming message_start event (#45376)

Signed-off-by: Wayne Chiu <waynehacking8@gmail.com>

* [Bugfix] Replace deprecated Qwen2VLImageProcessorFast with Qwen2VLImageProcessor (#42700)

Signed-off-by: abinggo <107740309+abinggo@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

* [CI] Wait for SSL cert refresher events in the test (#45489)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

* [Render] Add `/derender` endpoints for disaggregated postprocessing (#43606)

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

* [Bugfix] Return the tokenizer from maybe_make_thread_pool so it survives pickling (#45460)

Signed-off-by: Wayne Chiu <waynehacking8@gmail.com>

* [Doc] Fix uv dependency resolution failure for setuptools during CPU source builds (x86 & ARM) (#45412)

Signed-off-by: midas <the.anon.github@gmail.com>

* [Model Runner V2] Fix `openai.InternalServerError: Error code: 500 - 'list index out of range'` (#45467)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* Treat null completion max_tokens like the default (#45491)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

* [CI Bug] Fix `ValueError: There is no module or parameter named 'model.vision_tower.vision_model'` (#45478)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* [Security] Add timeout guard for regex compilation in structured outp… (#45118)

Signed-off-by: jperezde <jperezde@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

* [Security] Fix DoS via prompt_embeds on M-RoPE models (#45252)

Signed-off-by: jperezde <jperezde@redhat.com>

* Fix docs build on `main` (#45536)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

* [Bugfix] Reject structured outputs for diffusion decoders with a clear error (#45468)

Signed-off-by: Wayne Chiu <waynehacking8@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

* [Perf] SM90 cutlass fp8 mm supports odd M by swap_ab, 180~290% kernel performance improvement (#44572)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Core] Simplify MRV2 async output handling (#45442)

* [Bugfix] nightly Docker images crash with ImportError: AnthropicOutputConfig since May 28 (#44795)

Signed-off-by: achyuthan.s <113010327+Achyuthan-S@users.noreply.github.com>
Signed-off-by: Achyuthan S <achyuthan.sivasankar@gmail.com>
Signed-off-by: Achyuthan Sivasankar <achyuthan.sivasankar@gmail.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>

* [Build] Fix CUDA arch build coverage gaps (#45277)

Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Xin Li <xinli-sw@users.noreply.github.com>
Co-authored-by: ShawRong <ShawRong@users.noreply.github.com>
Co-authored-by: Change72 <Change72@users.noreply.github.com>

* [V1][Spec Decode] Add Dynamic SD (#32374)

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>

* [Bugfix][DCP] Fix illegal memory access in DCP a2a decode under full CUDA graphs (#45487)

* [XPU] Support int4 group_size=32 W4A16 MoE (#45136)

Signed-off-by: Marceli Fylcek <marceli.fylcek@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

* [ROCm][Perf] Enable W4A16 FlyDSL MoE (#44400)

Signed-off-by: amd-asalykov <asalykov@amd.com>
Signed-off-by: Amanzhol Salykov <asalykov@amd.com>

* [Perf] Use bisect for mm feature lookup in model runner v2 (#45566)

Signed-off-by: Roger Wang <hey@rogerw.io>

* [BugFix] Fix prompt_embeds for multimodal models (#45383)

Signed-off-by: ruinan ma <r7ma3088@gmail.com>

* Added real  /v1/embeddings support for messages + chat_template_kw  (#45173)

Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>

* [Bugfix][Model] Validate runai_streamer model_loader_extra_config (#45291)

Signed-off-by: Ting Sun <suntcrick@gmail.com>

* [Bugfix] Stream Llama4 weight loading to avoid host-OOM with copy-returning loaders (#44645)

Signed-off-by: Noa Neria <nneria@nvidia.com>

* [XPU] Enable sequence parallel support for XPU (#38608)

Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Signed-off-by: Chaojun,Zhang <chaojun.zhang@intel.com>

* [Bugfix][CPU] Honor cgroup memory limit when computing KV cache size (#45086)

Signed-off-by: baoloongmao <baoloongmao@tencent.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>

* [CPU] Refine CPU attention frontend (#45391)

Signed-off-by: jiang1.li <jiang1.li@intel.com>

* [Bugfix][CI] Update Dockerfile dependency graph PNG (#45602)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

* [Frontend] Add Streaming Parser Engine and new Qwen3 Parser (#45413)

Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>

* Fix included router missing path for `FastAPI >=0.137` (#45629)

Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

* [Bugfix][V1] Split V2 model-runner attention groups on num_heads_q (#45564)

Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>

* [Model] Remove XverseForCausalLM (#45638)

Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

* [Feature][Frontend] Report multimodal token counts in usage.prompt_tokens_details (#45458)

Signed-off-by: Ting Sun <suntcrick@gmail.com>

* [Bugfix] Reject out-of-range temperature values in SamplingParams (#44965)

Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>

* [Bugfix][Rust] Sync EngineCoreReadyResponse with the Python dataclass (#45557)

Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Will Eaton <weaton@redhat.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>

* [Rust Frontend] Add external→internal request-id map for abort() (#45137)

Signed-off-by: Sahil Singh <sahiilsiingh37@gmail.com>

* [Models] Fix MiMo v2.x QKV TP sharding + FP4 support (#45200)

Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Rust Frontend] Support `parallel_tool_calls = false` (#44760)

Signed-off-by: zhoujinyu <2319109590@qq.com>

* [Bugfix][Rust Frontend] Make metrics respect --served-model-name (#45465)

Signed-off-by: reidliu41 <reid201711@gmail.com>

* [XPU] skip UT test_with_ngram_gpu_spec_decoding (#44423)

Signed-off-by: Lai, Yejing <yejing.lai@intel.com>

* [ROCm][Doc] Add installation notes about python version requirement (#45671)

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>

* [Docs] Update the online serving docs. (#45676)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

* [Bugfix] Unset HF's default max_new_tokens for DiffusionGemma (#45417)

Signed-off-by: Martin Kukla <martin.kukla@cantab.net>

* (security) Enforce audio upload size limit before full file materialization (#45510)

Signed-off-by: jperezde <jperezde@redhat.com>

* Fix the E8M0 scale computation in the MXFP4 (W4A4) MOE CUTLASS kernel (#43557)

Signed-off-by: Xin He <xin3.he@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

* Remove redundant Triton KV cache dtype asserts and enforce architectural support (fp8 >= sm89) (#43914)

Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>
Co-authored-by: Michael Gschwind <mgschwind@nvidia.com>

* [Bugfix] Two-phase KV allocation for cross-group prefix cache hits (supersedes #33775) (#44409)

Signed-off-by: Saddss <2872669061@qq.com>

* [Chore] Consolidate reasoning/tool parser attributes into unified Parser in chat serving (#45548)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

* [AMD][Bugfix][Quantization] Honor fused-name match in is_layer_skipped (#43981)

* [Model] Add MiniMax M3 support (#45381)

Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>

* [KV Offloading] Implement `reset_cache` for `TieringOffloadingManager` (#44541)

Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Bugfix] Chat Completions Harmony Refactor Clean up (#45464)

Signed-off-by: Yifan Zong <yzong@redhat.com>
Co-authored-by: Ben Browning <bbrownin@redhat.com>

* [Perf] Optimize DSv4 prefill chunk planning, 4.0% E2E Throughput Improvement (#45061)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* [Frontend] Skip structural tags for auto tool_choice without strict mode (#45600)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

* [Model Runner V2][Bugfix] Fix MRV2 LoRA warmup (#35536)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>

* Fix parallel_tool_calls: null treated as false instead of default true (#44955)

Signed-off-by: factnn <166481866+factnn@users.noreply.github.com>

* [Frontend] Replace legacy Gemma4 parsers with engine-based implementation (#45588)

Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>

* [Bugfix] Defer block freeing until in-flight steps finish under async scheduling + PD KV consumer (#45357)

Signed-off-by: llx-08 <2596671364@qq.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

* nixl_ep: Skip post-receive quantization for NVFP4 (#45606)

Signed-off-by: Itay Alroy <ialroy@nvidia.com>

* [EP] Query NIXL EP top-k index dtype (#45298)

Signed-off-by: Itay Alroy <ialroy@nvidia.com>

* [EP] Enable DBO with NIXL EP (#45275)

Signed-off-by: Itay Alroy <ialroy@nvidia.com>

* [DSV4][Minor] Fix supported KV cache dtypes (#44892)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>

* [Misc][Model] add io processor for query/document embeddings from ColBERT (jinaai/jina-colbert-v2) (#45210)

Signed-off-by: thomas <thomas.varghese@columbia.edu>

* [Rust Frontend] Support `max_logprobs` validation (#45674)

Signed-off-by: Bugen Zhao <i@bugenzhao.com>

* [Rust Frontend] Lower out-of-vocab validation to `text` layer (#45685)

Signed-off-by: Bugen Zhao <i@bugenzhao.com>

* [Multimodal] Add Qwen3-VL video loader (#44412)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

* [BugFix] Support async scheduling with prompt embeds for multimodal models (#45673)

Signed-off-by: Ruinan Ma <r7ma3088@gmail.com>

* [XPU] Fix Triton attn fp8/bf16 check failing (#45758)

Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>

* [Bugfix][Gemma4] Fix offline parser truncation, adjust_request token leak, and chat template sync (#45553)

Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>

* [Rust Frontend] Require `ModelConfig.vocab_size` to be present (#45696)

Signed-off-by: Bugen Zhao <i@bugenzhao.com>

* [Frontend] [Parser] Migrate Nemotron V3 to streaming parser engine  (#45755)

Signed-off-by: Ben Browning <bbrownin@redhat.com>

* [Core] Use fastsafetensors ParallelLoader for weight loading (#40183)

Signed-off-by: Git Bisector <gitbisector@gmail.com>
Signed-off-by: gitbisector <gitbisector@gmail.com>
Signed-off-by: git bisector <gitbisector@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

* Register parsed config classes before tokenizer init (#40299)

Signed-off-by: Bortlesboat <bortstheboat@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>

* [Misc] Added validation for Cohere /v2/embed input field exclusivity (#45640)

Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>

* [Cleanup] Remove dead env (#45777)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

* [Bug Fix] Allow pinned memory for WSL2 (#41496)

Signed-off-by: Jimmy Lee <hirejimmylee@gmail.com>

* [CPU] Support Gemma Diffusion (#45690)

Signed-off-by: jiang1.li <jiang1.li@intel.com>

* [Bugfix] Prevent cuMemcpyBatchAsync segfault with MTP and KV offloading (#44784)

Signed-off-by: joshua <joshua.abraham@multicorewareinc.com>
Co-authored-by: joshua <joshua.abraham@multicorewareinc.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>

* [Frontend] Remove AsyncMicrobatchTokenizer. (#45759)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

* [Bugfix] Fix trtllm fused allreduce+rms_norm for transformers backend (#45307)

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>

* [XPU][CI] add intel xpu cases for nightly CI (#44372)

Signed-off-by: wenjun.liu <wenjun.liu@intel.com>
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
Co-authored-by: zengxian <xiangdong.zeng@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

* [Misc]Clean up useless test (#45792)

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

* Add Triton recompile detection (#45631)

Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>

* [MM][Perf][CG] Support dual-path ViT full CUDA graph for DeepSeek-OCR (#43586)

Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

* [KV Connector][Mooncake] Pipeline-parallel support for PD-disaggregated serving with Mooncake connector (#44528)

Signed-off-by: hanhan.hank <hanhan.hank@bytedance.com>
Signed-off-by: Hank Han <hanhan7630@outlook.com>

* [Refactor] Remove `Fp8OnlineLinearMethod` as scheduled (#45463)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [ZenCPU] Add zencpu Platform Runtime Logging and Docs (#42726)

Signed-off-by: Lalithnarayan C <Lalithnarayan.C@amd.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

* [ROCm][CI] Gate incompatible HF references on Transformers v5 (#41532)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

* [Quant] Support modelopt_mixed on Ampere (SM80/SM86) (#45306)

Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>

* [Bugfix][MoE] Restore routed output unpadding before shared expert add (#45707)

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Perf] Add VLLM_TRITON_FORCE_FIRST_CONFIG to skip Triton autotuning (#42425)

Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
Co-authored-by: Claude <noreply@anthropic.com>

* [CI] Fix attention benchmark smoke test (#45728)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>

* [Rust Frontend] Add CORS support (#45753)

Signed-off-by: Tahsin Tunan <tahsintunan@gmail.com>

* [Bugfix] Fix FlashMLA sparse accuracy with topk_length and zero-init padding (#36616)

Signed-off-by: AjAnubolu <anuboluajay@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>

* [Kernel][Helion][1/N] Add Helion kernel for rms_norm_per_block_quant (#36895)

Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>

* feat: MLA prefill enable FA4 fp8 output (#43050)

Signed-off-by: Carl You <4531192+carlyou@users.noreply.github.com>

* [ROCm][Cleanup] Remove stale AITER FA hybrid KV-cache TODO (#44178)

Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

* [Model] Add HrmTextForCausalLM (Hierarchical Reasoning Model — Text) (#43098)

Signed-off-by: Wuyifei <wuyifei@me.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

* Upgrade tpu-inference to v0.22.1 (#45793)

* [ROCm][CI] Patch conftest to resolve occasional OOMs (#45722)

Signed-off-by: Micah Williamson <micah.williamson@amd.com>

* [Model Runner V2] Enable GraniteMOE for MRv2 by default (#45461)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* [Model] Remove Dots1ForCausalLM (#45637)

Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

* [Bugfix][Core] Fall back when numactl --membind is blocked in constrained containers (#45438)

Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>

* [KVConnector][MoRIIO] Allow overriding the advertised host IP (#45488)

Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* [KV Connector][Mooncake] Add cache_prefix to namespace store keys (#45767)

Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* [Frontend] Add Streaming Parser Engine and new MinimaxM2 Parser (#45701)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>

* [Bugfix] Fix Qwen3 prompt tool-call reasoning false positive (#45763)

Signed-off-by: Alex Bilichenko <alexbi29@users.noreply.github.com>
Co-authored-by: Alex Bilichenko <alexbi29@users.noreply.github.com>

* [PERF] Fuse multi-group block table staged writes (#44944)

Signed-off-by: jesse <szxfml@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>

* [ROCm][Quant] mxfp8 moe/linear gfx950 tuning for MiniMax-M3 (#45725)

Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>

* [Misc] Update Mergify tool-calling label  (#45853)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

* [Core] Add prefill step cadence for better non-PD DP balancing (#44558)

Signed-off-by: Nick Hill <nickhill123@gmail.com>

* [ROCm][CI] fix multimodel run cmds (#45858)

Signed-off-by: Divakar Verma <divakar.verma@amd.com>

* [Bugfix] Gemma4: skip forced JSON for required/named tool choice (#45795)

Signed-off-by: Federico Iezzi <fiezzi@google.com>

* [Kernel] Support GLM-5 dimensions for TRT-LLM ragged MLA prefill (#43525)

Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>

* Apply LRU policy only to proper cache entries (#42656)

Signed-off-by: Stanislaw Wozniak <stw@zurich.ibm.com>

* [Kernel] Support DS Mamba tail copy for MTP align mode (#45473)

Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>

* [XPU][CI] fix server test file path (#45870)

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

* [Bugfix] Fix MoE model load OOM in FlashInfer_TRTLLM  backend with sleep mode (#45589)

Signed-off-by: Dakai An <dakaian108@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Bugfix][Gemma4] Fix parsing when thinking is disabled (#45832)

Signed-off-by: Federico Iezzi <fiezzi@google.com>

* [CI] Run pre-commit on self-hosted vllm-runners (#45865)

Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* [XPU] Fix test_spec_decode_logprobs: use FLASH_ATTN for XPU in GPU_DETERMINISM_KWARGS (#44468)

Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

* [Bugfix][ROCm] Fix MiniMax-M3 FP8 KV cache dtype (#45720)

Signed-off-by: Cam Quilici <cjquilici@gmail.com>
Signed-off-by: Cameron Quilici <cjquilici@gmail.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

* [Bugfix][ROCm] Fix FP8 per-tensor scale rank mismatch causing Inductor assertion failure (#44912)

Signed-off-by: nehmathe2 <nehmathe2@gmail.com>
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Signed-off-by: nehmathe <nehmathe@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>

* [ModelRunnerV2] Various model/config compatibility fixes (#45868)

Signed-off-by: Nick Hill <nickhill123@gmail.com>

* [Bugfix][V1] Clean up compiled-model bytecode hooks on VllmRunner exit (#45195)

Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [FlexAttention] make custom mask mods fully cudagraphable (#45232)

Signed-off-by: Angel Li <liangel@meta.com>

* [M3] Tune Triton indexer score decode for spec-decode (#45743)

Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [CI][NIXL] Pin NIXL to 1.2.0 (#45843)

Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Itay Alroy <75032521+itayalroy@users.noreply.github.com>
Co-authored-by: ovidiusm <ovidium@nvidia.com>

* [M3] Enable FP8 sparse GQA (#45744)

Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

* [Bugfix][Quantization] Reject unsupported compressed tensors KV cache schemes (#45312)

Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [BugFix][CI] Fix scheduler plugin test (#45897)

Signed-off-by: Nick Hill <nickhill123@gmail.com>

* [Rust Frontend] Support prompt-only completions (#44938)

Signed-off-by: reidliu41 <reid201711@gmail.com>

* [Rust Frontend] Add /abort_requests endpoint (#44382)

Signed-off-by: Sahil Singh <sahiilsiingh37@gmail.com>

* [Rust Frontend] Add serde defaults for omit_defaults fields in `EngineCoreSamplingParams` (#45848)

Signed-off-by: Will Eaton <weaton@redhat.com>

* [Kernel] Add weightless RMSNorm CUDA kernels for has_weight=False (#41430) (#44109)

Signed-off-by: hello-args <args.sarkar@gmail.com>

* [Misc] Validate Cohere Embed Mixed Content Payloads (#45873)

Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>

* [Rust Frontend] Support hybrid/external DP LB in Python supervised bootstrap (#45805)

Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>

* [KV Connector][Offloading] Avoid blocking the engine to flush offloads on idle (#45595)

Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Signed-off-by: Itay Etelis <Itay.etelis@gmail.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Itay Etelis <Itay.etelis@gmail.com>

* [Bugfix] Fixes MiniCPM-O resampler device placement to avoid tensor device mismatch (#42332)

Signed-off-by: j9smith <j.smith9103@outlook.com>

* [Bugfix][Gemma4] Pre-initialise streaming reasoning state when prompt ends inside an open `<|channel>` (fixes #45834) (#45852)

Signed-off-by: nikhilesh-csa <nchhetri@csa1.com>

* [Bugfix][test] Use Salesforce/wikitext for ppl tests (#45913)

Co-authored-by: wentian-byte <192079369+wentian-byte@users.noreply.github.com>

* fix(security): enforce audio decode duration limit in chat completions path (#45908)

Signed-off-by: jperezde <jperezde@redhat.com>

* [ROCm][Bugfix]: Fallback GFX942 sparse MLA ops to Triton (#45782)

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>

* docs, kv_offloading: add docs for selective offload (#45279)

Signed-off-by: Angelo Ruocco <ang@zurich.ibm.com>

* [ROCm][Quant] Minimax-M3:  Enable fp8_per_channel for bf16 weights on mi300x (#45854)

Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

* [MM][Perf][CG] Support ViT full CUDA graph for Kimi-VL (#41992)

Signed-off-by: oguz <oguzhankir17@gmail.com>

* [CI/Build] Avoid duplicate ViT CG test introduced by accident (#45654)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

* [XPU] Fix test_logprobs_e2e import error: pin lm-eval[api]>=0.4.12 (#44469)

Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>

* [quant][autoround]Refactor INC quantization into package with INCScheme orchestrator (#40601)

Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: Zhenzhong1 <zhenzhong.xu@intel.com>
Signed-off-by: Zhenzhong Xu <zhenzhong.xu@intel.com>
Co-authored-by: n1ck-guo <heng.guo@intel.com>
Co-authored-by: Zhenzhong1 <zhenzhong.xu@intel.com>

* [ROCm][AITER][Quark] Tag per-channel FP8 weights as PER_CHANNEL so AITER pre-shuffled GEMM is selected (#44626)

Signed-off-by: Xavier Aguilar <xavier.aguilarfruto@amd.com>

* Feature: Enable Flashinfer non-gated MoE bf16 (#43853)

Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>

* [DSv4 Perf] DSv4 flashinfer sparse index cache for metadata, 2%~4% TTFT improvement (#45863)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* [Kernel][Helion][1/N] Add Helion kernel for rms_norm_dynamic_per_token_quant (#34432)

Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>

* [Bugfix][PD] Fix DSV4 disaggregated serving (#45831)

Signed-off-by: ZhanqiuHu <zhu@redhat.com>

* [Bugfix] Pass TP group to FlashInfer all-reduce fusion (#45917)

Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>

* [Log] Update deepgemm log (#45857)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* [DSV4 Perf] Optimize dsv4 cudagraph by reducing `eager_break_during_capture`, 26.8% ~ 27.9% E2E TTFT improvement (#45309)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* [feature] MiniMax-M3-MXFP4 support added (#45896)

Signed-off-by: Qiang Li <qiang.li2@amd.com>

* [Bugfix] MiniMax-M3 (AMD): add packed_modules_mapping and pass swiglu… (#45794)

Signed-off-by: wangjiaxin99 <jiaxwang@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>

* [Refactor] Remove dead quantization code and tests (#45454)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

* [Bugfix][Gemma4] Render reasoning on assistant turns without tool_calls (#45867)

Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>

* [Bugfix][Model] Validate DefaultModelLoader / LoadConfig and fail with clear errors (#45196)

Signed-off-by: Ting Sun <suntcrick@gmail.com>

* [BUG] fix hidden states nan for hybrid attention models (#45849)

Signed-off-by: shanjiaz <hezhao@redhat.com>
Co-authored-by: shanjiaz <hezhao@redhat.com>

* [Bugfix] Fix NixlConnector handshake block_len validation for GQA-replicated KV heads (#45879)

Signed-off-by: Oseltamivir <58582368+Oseltamivir@users.noreply.github.com>
Co-authored-by: waynehacking8 <waynehacking8@gmail.com>

* Revert "[DSV4 Perf] Optimize dsv4 cudagraph by reducing `eager_break_during_capture`" (#45309) (#45972)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* [XPU][CI] add model runner v2 into CI (#44650)

Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>

* [CI/Build][Bugfix] Fix SD LoRA  (#45941)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

* [Bugfix] Complete one-shot fused all-reduce PDL at end to avoid NaN (#45448)

* [Rust Frontend][Perf] O(n) argument scan in tool parser (#45826)

Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>

* [XPU] Fix FP8 block-scaled scheme selection on non-CUDA platforms (#43958)

Signed-off-by: Lai, Yejing <yejing.lai@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

* [Rust Frontend] Validate tokenized bad_words vocabulary range (#45876)

Signed-off-by: reidliu41 <reid201711@gmail.com>

* [CPUOffloading] Guard CPU eviction check (#45757)

Signed-off-by: Varun Sundar Rabindranath <varun-sundar-rabindranath@h100-01.nemg-001.lab.rdu2.dc.redhat.com>
Co-authored-by: Varun Sundar Rabindranath <varun-sundar-rabindranath@h100-01.nemg-001.lab.rdu2.dc.redhat.com>

* [SimpleCPUOffloadConnector]: Add support for reset_cache() (#39726)

Signed-off-by: Jonathan Chen <chenleejonathan@gmail.com>
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* [Kernel] Add PDL support for DeepGEMM kernel (#42996)

Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>

* [Fix][KV offload] Defer `on_request_finished` until in-flight transfers drain (#45823)

Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>

* [Refactor] Remove dead cutlass mxfp8 code (#44681)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>

* [KV Offloading] Remove dummy worker-side stats from OffloadingConnector (#45905)

Signed-off-by: Alex <alex.tech.lab@outlook.com>
Signed-off-by: AlexHuang <jihuihuang@alexai.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>

* [Test][KV Connector] Add request_finished fence population tests for offloading scheduler (#45679)

Signed-off-by: Alex <alex.tech.lab@outlook.com>
Signed-off-by: AlexHuang <jihuihuang@future.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>

* Revert "[Kernel] Add PDL support for DeepGEMM kernel" (#45999)

* [XPU] Update nixl to v0.10.1 in Dockerfile (#40287)

Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

* fix(layernorm): route weightless RMSNorm to native impl

The vllm_c rms_norm/fused_add_rms_norm guards claimed support for
weight=None, but torch.ops._C.rms_norm cannot take a None/undefined weight
(fails with 'Not yet supported ScalarType'). Weightless norms (e.g. Gemma4
v_norm, has_weight=False) now correctly fall back to the native impl.

* test(steering): retarget key-coercion test at coerce_steering_spec

The SetSteeringRequest.vectors field is intentionally dict[str, Any] (to
admit the packed wire form), so the model does not coerce inner layer keys;
coerce_steering_spec does. Test the actual coercion seam (which had no
direct coverage) instead of obsolete model-level behavior.

* fix(capture): skip broken consumer entry points instead of crashing

A single third-party capture-consumer plugin that fails to import (e.g.
one referencing a module not present in this build) previously crashed
_load_entry_points and took down all capture admission. Skip it with a
warning so other consumers keep working.

---------

Signed-off-by: Sean Chen <seachen@redhat.com>
Signed-off-by: Wentian Byte <3400259131@qq.com>
Signed-off-by: RickyChen / 陳昭儒 <ricky.chen@infinirc.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Yifan Zong <yzong@redhat.com>
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Signed-off-by: Neil Schemenauer <nas@arctrix.com>
Signed-off-by: jpwang <jpwang@smail.nju.edu.cn>
Signed-off-by: Hsiao-Yuan Chen <hy.c@Hsiao-YuandeMacBook-Pro.local>
Signed-off-by: littlecircle0730 <littlecircle0730@gmail.com>
Signed-off-by: littlecircle0730 <43994952+littlecircle0730@users.noreply.github.com>
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Sasindharan Sankar <sasindharansankar@email.com>
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Signed-off-by: varun sundar rabindranath <vsundarr@redhat.com>
Signed-off-by: Chris Leonard <chleonar@redhat.com>
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: allgather <all2allops@gmail.com>
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
Signed-off-by: Will Eaton <weaton@redhat.com>
Signed-off-by: Ma Jian <jian1.ma@intel.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: xiaguan <751080330@qq.com>
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>
Signed-off-by: jperezde <jperezde@redhat.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Signed-off-by: Sunita Nadampalli <nadampal@amazon.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Ethan Feng <ethan.fengch@gmail.com>
Signed-off-by: Thillai Chithambaram <thillaichithambaram.a@gmail.com>
Signed-off-by: Guan-Ming (Wesley) Chiu <guanmingchiu@gmail.com>
Signed-off-by: Guan-Ming (Wesley) Chiu <105915352+guan404ming@users.noreply.github.com>
Signed-off-by: srinivas_oo7 <sklinkedin0120@gmail.com>
Signed-off-by: Sai Sridhar <tarrasridhar1154@gmail.com>
Signed-off-by: Tahsin Tunan <tahsintunan@gmail.com>
Signed-off-by: vincentzed <207368749+vincentzed@users.noreply.github.com>
Signed-off-by: Jonas I. Liechti <j-i-l@t4d.ch>
Signed-off-by: zixi-qi <zixi@inferact.ai>
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Fangzhou Ai <fangzhouai@gmail.com>
Signed-off-by: khluu <khluu000@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Wayne Chiu <waynehacking8@gmail.com>
Signed-off-by: abinggo <107740309+abinggo@users.noreply.github.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Signed-off-by: midas <the.anon.github@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: achyuthan.s <113010327+Achyuthan-S@users.noreply.github.com>
Signed-off-by: Achyuthan S <achyuthan.sivasankar@gmail.com>
Signed-off-by: Achyuthan Sivasankar <achyuthan.sivasankar@gmail.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Signed-off-by: Marceli Fylcek <marceli.fylcek@intel.com>
Signed-off-by: amd-asalykov <asalykov@amd.com>
Signed-off-by: Amanzhol Salykov <asalykov@amd.com>
Signed-off-by: ruinan ma <r7ma3088@gmail.com>
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Signed-off-by: Noa Neria <nneria@nvidia.com>
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Signed-off-by: Chaojun,Zhang <chaojun.zhang@intel.com>
Signed-off-by: baoloongmao <baoloongmao@tencent.com>
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
Signed-off-by: Sahil Singh <sahiilsiingh37@gmail.com>
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Signed-off-by: zhoujinyu <2319109590@qq.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
Signed-off-by: Lai, Yejing <yejing.lai@intel.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: Martin Kukla <martin.kukla@cantab.net>
Signed-off-by: Xin He <xin3.he@intel.com>
Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>
Signed-off-by: Saddss <2872669061@qq.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: factnn <166481866+factnn@users.noreply.github.com>
Signed-off-by: llx-08 <2596671364@qq.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: thomas <thomas.varghese@columbia.edu>
Signed-off-by: Ruinan Ma <r7ma3088@gmail.com>
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Signed-off-by: Git Bisector <gitbisector@gmail.com>
Signed-off-by: gitbisector <gitbisector@gmail.com>
Signed-off-by: git bisector <gitbisector@gmail.com>
Signed-off-by: Bortlesboat <bortstheboat@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Jimmy Lee <hirejimmylee@gmail.com>
Signed-off-by: joshua <joshua.abraham@multicorewareinc.com>
Signed-off-by: wenjun.liu <wenjun.liu@intel.com>
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: hanhan.hank <hanhan.hank@bytedance.com>
Signed-off-by: Hank Han <hanhan7630@outlook.com>
Signed-off-by: Lalithnarayan C <Lalithnarayan.C@amd.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
Signed-off-by: AjAnubolu <anuboluajay@gmail.com>
Signed-off-by: Carl You <4531192+carlyou@users.noreply.github.com>
Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
Signed-off-by: Wuyifei <wuyifei@me.com>
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: Alex Bilichenko <alexbi29@users.noreply.github.com>
Signed-off-by: jesse <szxfml@gmail.com>
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: Federico Iezzi <fiezzi@google.com>
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
Signed-off-by: Stanislaw Wozniak <stw@zurich.ibm.com>
Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Cam Quilici <cjquilici@gmail.com>
Signed-off-by: Cameron Quilici <cjquilici@gmail.com>
Signed-off-by: nehmathe2 <nehmathe2@gmail.com>
Signed-off-by: nehmathe <nehmathe@amd.com>
Signed-off-by: Angel Li <liangel@meta.com>
Signed-off-by: Itay Alroy <75032521+itayalroy@users.noreply.github.com>
Signed-off-by: hello-args <args.sarkar@gmail.com>
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Signed-off-by: Itay Etelis <Itay.etelis@gmail.com>
Signed-off-by: j9smith <j.smith9103@outlook.com>
Signed-off-by: nikhilesh-csa <nchhetri@csa1.com>
Signed-off-by: Angelo Ruocco <ang@zurich.ibm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: oguz <oguzhankir17@gmail.com>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: Zhenzhong1 <zhenzhong.xu@intel.com>
Signed-off-by: Zhenzhong Xu <zhenzhong.xu@intel.com>
Signed-off-by: Xavier Aguilar <xavier.aguilarfruto@amd.com>
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Signed-off-by: ZhanqiuHu <zhu@redhat.com>
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
Signed-off-by: Qiang Li <qiang.li2@amd.com>
Signed-off-by: wangjiaxin99 <jiaxwang@amd.com>
Signed-off-by: shanjiaz <hezhao@redhat.com>
Signed-off-by: Oseltamivir <58582368+Oseltamivir@users.noreply.github.com>
Signed-off-by: Varun Sundar Rabindranath <varun-sundar-rabindranath@h100-01.nemg-001.lab.rdu2.dc.redhat.com>
Signed-off-by: Jonathan Chen <chenleejonathan@gmail.com>
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
Signed-off-by: Alex <alex.tech.lab@outlook.com>
Signed-off-by: AlexHuang <jihuihuang@alexai.com>
Signed-off-by: AlexHuang <jihuihuang@future.com>
Co-authored-by: Xiaohong (Sean) Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: wentian-byte <3400259131@qq.com>
Co-authored-by: Chao-Ju Chen <ricky.chen@infinirc.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Tiezhen WANG <38108242+xianbaoqian@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: yzong-rh <yzong@redhat.com>
Co-authored-by: Dao007forever <dao007forever@gmail.com>
Co-authored-by: Neil Schemenauer <nas-github@arctrix.com>
Co-authored-by: jpwang <jpwang@smail.nju.edu.cn>
Co-authored-by: littlecircle0730 <43994952+littlecircle0730@users.noreply.github.com>
Co-authored-by: Hsiao-Yuan Chen <hy.c@Hsiao-YuandeMacBook-Pro.local>
Co-authored-by: Or Ozeri <or@ozery.com>
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
Co-authored-by: vLLM Contributor <contributor@vllm.ai>
Co-authored-by: Ting SUN <suntcrick@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: sasindharan <117493393+sasindharan@users.noreply.github.com>
Co-authored-by: Sasindharan Sankar <sasindharansankar@email.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: varun sundar rabindranath <vsundarr@redhat.com>
Co-authored-by: Chris Leonard <chleonar@redhat.com>
Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Martin Kukla <martin.kukla@cantab.net>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Dipika Sikka <dsikka@redhat.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Alec Kohlhoff <134344302+aleckohlhoff@users.noreply.github.com>
Co-authored-by: Porras Huang <20535584+porrashuang@users.noreply.github.com>
Co-authored-by: scoootscooob <167050519+scoootscooob@users.noreply.github.com>
Co-authored-by: allgather <all2allops@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: Yuwen Zhou <yuwen.zhou@intel.com>
Co-authored-by: Will Eaton <wseaton@users.noreply.github.com>
Co-authored-by: Ma Jian <jian1.ma@intel.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: cjackal <44624812+cjackal@users.noreply.github.com>
Co-authored-by: JinYan Su <jinyansu792@gmail.com>
Co-authored-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>
Co-authored-by: Juan Pérez de Algaba <124347725+jperezdealgaba@users.noreply.github.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: liuzhenwei <zhenweiliu@habana.ai>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Ethan Feng <ethan.fengch@gmail.com>
Co-authored-by: Thillai Chithambaram <79466435+thillai-c@users.noreply.github.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Guan-Ming (Wesley) Chiu <105915352+guan404ming@users.noreply.github.com>
Co-authored-by: Srinivas Krovvidi <194645829+Srinivasoo7@users.noreply.github.com>
Co-authored-by: srinivas_oo7 <sklinkedin0120@gmail.com>
Co-authored-by: Sai Sridhar Tarra <117087864+sridhar-3009@users.noreply.github.com>
Co-authored-by: Tahsin Tunan <tahsintunan@gmail.com>
Co-authored-by: Yi Zhong <207368749+vincentzed@users.noreply.github.com>
Co-authored-by: Jonas I. Liechti <j-i-l@t4d.ch>
Co-authored-by: qizixi <22851944+zixi-qi@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Ryan Rock <ryan.rock@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: WEI CHENG CHIU <waynehacking8@gmail.com>
Co-authored-by: longguo <107740309+abinggo@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: midas <the.anon.github@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: achyuthan.s <113010327+Achyuthan-S@users.noreply.github.com>
Co-authored-by: Xin Li <xinli-sw@users.noreply.github.com>
Co-authored-by: ShawRong <ShawRong@users.noreply.github.com>
Co-authored-by: Change72 <Change72@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Jeff (Junze) Ma <93145857+majunze2001@users.noreply.github.com>
Co-authored-by: Marceli Fylcek <marceli.fylcek@intel.com>
Co-authored-by: Amanzhol Salykov <asalykov@amd.com>
Co-authored-by: Michael Ma <97484148+mrn3088@users.noreply.github.com>
Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Noa Neria <nneria@nvidia.com>
Co-authored-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: maobaolong <baoloongmao@tencent.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
Co-authored-by: Peter Pan <peter.pan@daocloud.io>
Co-authored-by: Sahil Singh <sahiilsiingh37@gmail.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: FAUST <2319109590@qq.com>
Co-authored-by: Reid <61492567+reidliu41@users.noreply.github.com>
Co-authored-by: Yejing Lai <yejing.lai@intel.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Xin He <xin3.he@intel.com>
Co-authored-by: Mike G <180722391+mikekg@users.noreply.github.com>
Co-authored-by: Michael Gschwind <mgschwind@nvidia.com>
Co-authored-by: Saddss <108515797+Saddss@users.noreply.github.com>
Co-authored-by: RoyWang <Roy.Wang@amd.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Ronen Schaffer <ronen.schaffer@ibm.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Zang Peiyu <166481866+factnn@users.noreply.github.com>
Co-authored-by: llx <54896441+llx-08@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Itay Alroy <75032521+itayalroy@users.noreply.github.com>
Co-authored-by: xx-thomas <113865951+xx-thomas@users.noreply.github.com>
Co-authored-by: Luciano Martins <22145370+lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: gitbisector <gitbisector@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Andrew Barnes <bortstheboat@gmail.com>
Co-authored-by: Jimmy Lee <58957694+thisisjimmyfb@users.noreply.github.com>
Co-authored-by: joshua abraham <132982099+JOSH1024@users.noreply.github.com>
Co-authored-by: joshua <joshua.abraham@multicorewareinc.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: wenjun liu <wenjun.liu@intel.com>
Co-authored-by: zengxian <xiangdong.zeng@intel.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
Co-authored-by: Hank Han <hanhan7630@outlook.com>
Co-authored-by: Lalithnarayan C <Lalithnarayan.C@amd.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Francesco Fusco <ffu@zurich.ibm.com>
Co-authored-by: Ajay Anubolu <124525760+AjAnubolu@users.noreply.github.com>
Co-authored-by: Carl Y <4531192+carlyou@users.noreply.github.com>
Co-authored-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
Co-authored-by: yifei wu <50608184+abcd1927@users.noreply.github.com>
Co-authored-by: Sting Lin <sting.lin@cienet.com>
Co-authored-by: kourosh hakhamaneshi <31483498+kouroshHakha@users.noreply.github.com>
Co-authored-by: alexbi29 <32223381+alexbi29@users.noreply.github.com>
Co-authored-by: Alex Bilichenko <alexbi29@users.noreply.github.com>
Co-authored-by: Song Zhixin <szxfml@gmail.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Federico <federico.iezzi@gmail.com>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
Co-authored-by: Stan Wozniak <77159600+s3woz@users.noreply.github.com>
Co-authored-by: sungsoo ha <sungsooh@nvidia.com>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>
Co-authored-by: Dakai An <77474977+andakai@users.noreply.github.com>
Co-authored-by: Federico <fiezzi@google.com>
Co-authored-by: Cameron Quilici <cjquilici@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: nehmathe2 <nehmathe@amd.com>
Co-authored-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: liangel-02 <liangel@meta.com>
Co-authored-by: ovidiusm <ovidium@nvidia.com>
Co-authored-by: arghyadeep sarkar <args.sarkar@gmail.com>
Co-authored-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <Itay.etelis@gmail.com>
Co-authored-by: Joel Smith <j.smith9103@outlook.com>
Co-authored-by: Nikhilesh Chhetri <106703537+nikhilesh-csa@users.noreply.github.com>
Co-authored-by: wentian-byte <192079369+wentian-byte@users.noreply.github.com>
Co-authored-by: Angelo Ruocco <ang@zurich.ibm.com>
Co-authored-by: Oğuzhan KIR <86883236+oguzhankir@users.noreply.github.com>
Co-authored-by: Yi Liu <yi4.liu@intel.com>
Co-authored-by: n1ck-guo <heng.guo@intel.com>
Co-authored-by: Zhenzhong1 <zhenzhong.xu@intel.com>
Co-authored-by: xaguilar-amd <xavier.aguilarfruto@amd.com>
Co-authored-by: amirkl94 <203507526+amirkl94@users.noreply.github.com>
Co-authored-by: zhanqiuhu <49648934+ZhanqiuHu@users.noreply.github.com>
Co-authored-by: danisereb <daserebrenik@nvidia.com>
Co-authored-by: qli88 <qiang.li2@amd.com>
Co-authored-by: wangjiaxin99 <jiaxwang@amd.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Co-authored-by: shanjiaz <zsjwpianpian@gmail.com>
Co-authored-by: shanjiaz <hezhao@redhat.com>
Co-authored-by: Bryan Shan <58582368+Oseltamivir@users.noreply.github.com>
Co-authored-by: Ace Eldeib <aeldeib@coreweave.com>
Co-authored-by: Varun Sundar Rabindranath <varun-sundar-rabindranath@h100-01.nemg-001.lab.rdu2.dc.redhat.com>
Co-authored-by: Jonathan Chen <chenleejonathan@gmail.com>
Co-authored-by: AlexHuang <alex.tech.lab@outlook.com>
nkzhenhua pushed a commit to nkzhenhua/vllm that referenced this pull request Jun 24, 2026
@AndreasKaratzas @nkzhenhua
[ROCm][CI] Gate incompatible HF references on Transformers v5 (vllm-p…
5c17ee9 
…roject#41532)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@claude claude[bot] claude[bot] left review comments
@hmellor hmellor hmellor approved these changes
@DarkLight1337 DarkLight1337 Awaiting requested review from DarkLight1337 DarkLight1337 is a code owner
@ywang96 ywang96 Awaiting requested review from ywang96 ywang96 is a code owner
@NickLucche NickLucche Awaiting requested review from NickLucche NickLucche is a code owner
@tjtanaa tjtanaa Awaiting requested review from tjtanaa tjtanaa is a code owner
@khluu khluu Awaiting requested review from khluu khluu is a code owner
+2 more reviewers
@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments
@eustlb eustlb eustlb approved these changes
Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

ci/build multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm

Projects

AMD
Status: Done

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

6 participants

@AndreasKaratzas @lashahub @hmellor @eustlb @tjtanaa @DarkLight1337