-
Notifications
You must be signed in to change notification settings - Fork 83
Pull requests: ROCm/ATOM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
perf(dsv4): adaptive BLOCK_K for csa_translate_pack
#1464
opened Jul 4, 2026 by
valarLip
Collaborator
Loading…
[ci][mesh] publish benchmark data on dashboard
#1461
opened Jul 3, 2026 by
wanzhenchn
Contributor
Loading…
[GLM5.2 FP8/MXFP4] optimize atom native GLM5.2
#1458
opened Jul 3, 2026 by
zejunchen-zejun
Collaborator
•
Draft
add SemiAnalysis aiperf install to ATOM image
#1457
opened Jul 3, 2026 by
Yuechguo
Contributor
Loading…
[atom-vllm] enable prefix cache for deepseek v4
#1454
opened Jul 3, 2026 by
whx-sjtu
Contributor
Loading…
Remove legacy proxy, update docs, and enhance scripts
#1447
opened Jul 3, 2026 by
Jasen2201
Contributor
Loading…
1 task
[Frontend] openai: multi-model tool-call parsing + reasoning (GLM / MiniMax-M3 / DSML)
#1443
opened Jul 2, 2026 by
yhl-amd
Contributor
Loading…
[Bugfix] Cancel inference on client disconnect + fix non-stream request leak
#1441
opened Jul 2, 2026 by
yhl-amd
Contributor
Loading…
[fix](qwen3.5): fix qwen3.5 full decode graph error
#1436
opened Jul 2, 2026 by
PerryZhang01
Contributor
Loading…
feat(openai): add tool calling support with GPT-OSS Harmony parser
#1431
opened Jul 1, 2026 by
seungrokj
Contributor
Loading…
3 tasks
[sgl-atom] support Qwen3-32B in SGLang accuracy CI on MI308
#1430
opened Jul 1, 2026 by
zhangxinyuanliuhengyu
Contributor
Loading…
Add feature to parse Hermes <tool_call>{json}</tool_call> tool calls
#1427
opened Jul 1, 2026 by
hyukjlee
Contributor
Loading…
[Bugfix] DeepSeek-V4: content-addressed paged SWA fixes prefix-cache corruption (#1417)
#1423
opened Jul 1, 2026 by
yhl-amd
Contributor
Loading…
5 tasks done
feat(prezero): wire split-K GEMM prezero into MLA / MoE decode
#1421
opened Jun 30, 2026 by
ColorsWind
Loading…
[Spec Decode] Add DeepSeek-V4 DSpark speculative decoding
#1414
opened Jun 30, 2026 by
ZhangLirong-amd
Collaborator
•
Draft
1 task
fix(rtpllm): adapt to RTP-LLM PyAttentionInputs host/device field rename
#1412
opened Jun 30, 2026 by
Jonathan-hwx
Loading…
1 task
[Enhancement] Supports per_block_fp8 format for online quantization
#1411
opened Jun 30, 2026 by
haoyangli0109
Contributor
Loading…
[VLLM plugin] fix(kimi): align input norm quant with attention quant
#1409
opened Jun 30, 2026 by
qichu-yun
Contributor
Loading…
1 task
[Feature] OFFLOAD: MultiConnector — run P/D (mooncake/moriio) + LMCache offload together
#1406
opened Jun 29, 2026 by
yhl-amd
Contributor
Loading…
2 tasks done
Previous Next
ProTip!
Adding no:label will show everything without a label.