Skip to content

Pull requests: ROCm/ATOM

New pull request New
182 Open 1,408 Closed
182 Open 1,408 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

fix(plugin): reuse vLLM PyNccl communicator
#1804 opened Aug 5, 2026 by XiaobingSuper Contributor • Draft
2
fix: include content="" in streaming role chunk to match OpenAI/vLLM shape
#1803 opened Aug 5, 2026 by shantipriya-amd Loading…
1 task done
4
[SGL+ATOM]fix[plugin]: guard GLM flat fmoe on MI308
#1798 opened Aug 5, 2026 by zhangxinyuanliuhengyu Contributor Loading…
1
Feat/v4 wo a mxscale bmm
#1795 opened Aug 5, 2026 by yzhou103 Contributor • Draft
1 task
1
[feat](vllm): upgrade vllm to 0.26.1
#1794 opened Aug 5, 2026 by zejunchen-zejun Collaborator • Draft
1 task
3
fix(deepseek_v4): gfx942 dtype-dialect and MXFP4 swizzle fixes for DeepSeek-V4-Flash
#1793 opened Aug 4, 2026 by AMD-melliott Loading…
1 task done
1
[vLLM-ATOM] Support DSpark speculative decoding for Kimi-K3 ci:vllm
#1789 opened Aug 4, 2026 by whx-sjtu Contributor Loading…
4 of 5 tasks
1
optimize attn res ref fla and fuse all possible part around it ci:atom
#1788 opened Aug 4, 2026 by ganyi1996ppo Contributor Loading…
1 task
8
[feat]: support glm5 and glm52 in rtpllm
#1786 opened Aug 4, 2026 by zhiqchen-amd Loading…
1
[feat](k3): add k3 to precheckin and nightly test ci:vllm
#1783 opened Aug 4, 2026 by PerryZhang01 Contributor Loading…
1
Whn/kimi k3 multimodel
#1782 opened Aug 4, 2026 by HaonanWang98 Contributor Loading…
1 task
9
[feat][DCP] Enable DCP with fp8 MTP
#1781 opened Aug 4, 2026 by yitingw1 Contributor Loading…
1 task
1
random IMA fix
#1780 opened Aug 4, 2026 by gbyu-amd Contributor Loading…
1 task
sparsekv cache glm52 agentic task optimization
#1779 opened Aug 4, 2026 by Jasen2201 Contributor • Draft
1 task
27
[Doc] online quant best practices
#1777 opened Aug 3, 2026 by haoyangli0109 Contributor • Draft
1
[Kimi-K3] Enable align-mode mamba prefix caching (vLLM-ATOM)
#1773 opened Aug 3, 2026 by gbyu-amd Contributor Loading…
1 task
1
feat(kv-cache): content-addressed per-request state, so prefix hits are correct on stateful models
#1771 opened Aug 3, 2026 by valarLip Collaborator Loading…
1
Add Periodic Engine Status Log (Server Mode) ci:atom
#1770 opened Aug 3, 2026 by yitingw1 Contributor Loading…
1 task
1
[Feature] DeepSeek-V4 CSA prefix-state cache on SWA (native, no arena) ci:atom
#1769 opened Aug 1, 2026 by yhl-amd Contributor Loading…
3 tasks done
3
[Triton] [Gluon] [GFX9] [GFX12] Add triton/gluon support for EP+DP_attn
#1765 opened Aug 1, 2026 by k50112113 Collaborator • Draft
1
feat(glm): support GLM-5.2 DP attention
#1762 opened Jul 31, 2026 by wanzhenchn Contributor Loading…
3
[ATOM SGL] GLM 5.2 MTP Support ci:sglang
#1760 opened Jul 31, 2026 by ZhiweiYan-96 Contributor Loading…
1 task
30
support mamba prefix cache
#1759 opened Jul 31, 2026 by ganyi1996ppo Contributor Loading…
17
Add fake eplb for performance test
#1755 opened Jul 31, 2026 by junhaha666 Contributor Loading…
1
[k3] enable dual stream for shared expert and some fusions
#1752 opened Jul 30, 2026 by gbyu-amd Contributor Loading…
1 task
4
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.