Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
869 Open 11,237 Closed
869 Open 11,237 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[None][feat] Update CuTeDSL MegaMoE kernels
#16190 opened Jul 9, 2026 by Barry-Delaney Collaborator • Draft
@Barry-Delaney
[None][feat] Add --skip_requirements to build_wheel.py
#16188 opened Jul 9, 2026 by lucifer1004 Collaborator Loading…
@lucifer1004
3
[None][feat] Integrate KVCMv2 commit_min_snapshot in runtime
#16185 opened Jul 9, 2026 by jiaganc Collaborator • Draft
1 task done
@jiaganc
1
[TRTLLM-13231][feat] Support top_p_decay in the PyTorch TorchSampler
#16184 opened Jul 9, 2026 by zhaoyangwang-nvidia Collaborator • Draft
1 task done
@zhaoyangwang-nvidia
[TRTLLMINF-191][infra] Make S3 stdout echo opt-in
#16182 opened Jul 9, 2026 by niukuo Collaborator Loading…
1 task done
@niukuo
4
[None][fix] Improve scope conflict handling in Selector class
#16181 opened Jul 9, 2026 by yufeiwu-nv Collaborator Loading…
1 task done
@yufeiwu-nv
5
[https://nvbugs/6379333] [chore] Unwaive test cases
#16180 opened Jul 9, 2026 by kaiyux Member • Draft
1 task done
@kaiyux
6
[None][test] Fix MLA import path in attention perf harness
#16179 opened Jul 9, 2026 by ruodil Collaborator Loading…
1 task done
@ruodil
4
[None][perf] Prewarm DeepGEMM paged_mqa_logits_metadata JIT buckets
#16178 opened Jul 9, 2026 by chenfeiz0326 Collaborator Loading…
4 tasks done
@chenfeiz0326
4
[None][perf] Close Mamba hybrid warmup gap in autotuner warmup
#16177 opened Jul 9, 2026 by chenfeiz0326 Collaborator Loading…
3 tasks
@chenfeiz0326
4
[https://nvbugs/6430358][fix] mhc: make _FusedHcWorkspaceCache CUDA-graph-safe
#16176 opened Jul 9, 2026 by dc3671 Collaborator Loading…
@dc3671
8
[https://nvbugs/6411873][fix] DSV4: size KV constraint with num_extra_kv_tokens
#16173 opened Jul 9, 2026 by xguannv Contributor Loading…
1 task done
@xguannv
3
[https://nvbugs/6323074][fix] fix flaky hang issue for disagg gen-onl…
#16172 opened Jul 9, 2026 by bo-nv Collaborator Loading…
1 task done
@bo-nv
3
[https://nvbugs/6388153][fix] Relay PP sample states synchronously on…
#16170 opened Jul 9, 2026 by WeiHaocheng Collaborator Loading…
@WeiHaocheng
3
[https://nvbugs/6430674][fix] Surgical revert of PR #15838's dispatch guard removal: re-add…
#16167 opened Jul 9, 2026 by chenfeiz0326 Collaborator Loading…
2 tasks done
@chenfeiz0326
4
[None][fix] Remove redundant residual bound check in EAGLE3 hidden-state capture
#16165 opened Jul 9, 2026 by eopXD Collaborator Loading…
1 task done
@eopXD
4
[None][feat] BREAKING: add per-model transceiver runtime auto selection api-breaking Accepted LLM API contract change that is backwards-incompatible
#16164 opened Jul 9, 2026 by nv-xtf Collaborator Loading…
1 task done
@nv-xtf
6
[None][feat] Add FastWan2.2 TI2V-5B DMD pipeline (3-step text-to-video)
#16162 opened Jul 9, 2026 by Kambili • Draft
@Kambili
[None][fix] Prevent leaked ADP pad dummy from crashing the executor
#16161 opened Jul 9, 2026 by lingjiew • Draft
3 tasks done
@lingjiew
1
[TRTLLM-14198][refactor] Make FlashInfer a hard dependency for the Torch sampler api-compatible Accepted LLM API contract change that is backwards-compatible
#16160 opened Jul 9, 2026 by zhaoyangwang-nvidia Collaborator Loading…
1 task done
@zhaoyangwang-nvidia
18
[None][feat] Bind SourceIdentity to checkpoint artifacts
#16159 opened Jul 9, 2026 by chienchunhung Collaborator • Draft
@chienchunhung
3
[None][perf] Overlap scheduler and cross-attn fast path for enc-dec
#16158 opened Jul 9, 2026 by cascade812 Collaborator Loading…
@cascade812
11
[TRTLLM-12714][fix] Free CUDA-graph padding dummy KV caches before pool rebalance adjust()
#16157 opened Jul 9, 2026 by thorjohnsen Collaborator Loading…
@thorjohnsen
4
[None][fix] Dev nemotron hang
#16156 opened Jul 8, 2026 by 2ez4bz Collaborator • Draft
1 task done
@2ez4bz
8
[None][feat] Cosmos3 video-to-video (V2V) generation
#16155 opened Jul 8, 2026 by ishovkun Loading…
1 task done
@ishovkun
8
ProTip! Add no:assignee to see everything that’s not assigned.