Skip to content

Pull requests: ROCm/ATOM

New pull request New
144 Open 1,059 Closed
144 Open 1,059 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: FP8 MoE weight load in MI308
#1375 opened Jun 26, 2026 by zhaoan12-prc Contributor Loading…
2
add tbo support for m3
#1373 opened Jun 26, 2026 by zhuyuhua-v Collaborator • Draft
1 task
[atom-vllm] adapt DeepSeek V4 MTP for vLLM plugin
#1372 opened Jun 26, 2026 by whx-sjtu Contributor • Draft
[atom benchmark] add indexer cache for M3 in atom benchmark
#1371 opened Jun 26, 2026 by zejunchen-zejun Collaborator • Draft
support online quant for quark models
#1370 opened Jun 26, 2026 by gbyu-amd Contributor Loading…
1 task
2
Enable TBO Support & Fix Accuracy Regressions for Kimi K2.5
#1369 opened Jun 26, 2026 by jpy794 Loading…
1 task done
10
fix(pd): transfer MiniMax-M3 sparse indexer-key cache in disaggregation
#1368 opened Jun 26, 2026 by Jasen2201 Contributor Loading…
1 task
1
fix(server): batch stream-chunk dispatch
#1367 opened Jun 26, 2026 by ZhangLirong-amd Collaborator Loading…
1 task
2
[Enhancement] aglin online quantizaiton and offline quantization
#1365 opened Jun 26, 2026 by haoyangli0109 Contributor Loading…
[ATOM SGL] MTP Spec decode
#1361 opened Jun 26, 2026 by ZhiweiYan-96 Contributor Loading…
1 task
3
feat: add dtype option in LayerNorm class
#1359 opened Jun 25, 2026 by cpersson-amd Loading…
1 task done
2
fix(prefix-cache): bypass prefix caching for multimodal sequences
#1358 opened Jun 25, 2026 by carlushuang Collaborator Loading…
feat(gfx1151): custom head-dim-tiled Triton flash attention for Qwen3.x ViT
#1357 opened Jun 25, 2026 by carlushuang Collaborator Loading…
Triton GEMM Integration
#1355 opened Jun 25, 2026 by amirumoAMD Contributor • Draft
1 task
fix: convert weight scale shape[N, K/128] to [ceil(N/128), ceil(K/128)]
#1353 opened Jun 25, 2026 by JiaoliangYu Contributor • Draft
1 task
[fix](qwen): fix qwen3.5-35b accuracy
#1351 opened Jun 25, 2026 by PerryZhang01 Contributor • Draft
[fix](ci): mv plugin test to new node
#1350 opened Jun 25, 2026 by PerryZhang01 Contributor Loading…
[atom-sgl-vllm-ci] Modify Qwen3.5-35B-A3B-FP8 runner
#1349 opened Jun 25, 2026 by junyyang-amd Contributor Loading…
[minimax_m3] gate AR+RMSNorm fusion on ATOM_ENABLE_ALLREDUCE_RMSNORM_…
#1344 opened Jun 24, 2026 by zejunchen-zejun Collaborator • Draft
1 task
Enable MiniMax-M3 vLLM plugin path
#1342 opened Jun 24, 2026 by lirui927 Contributor • Draft
1 task
5
feat: add backend for moe
#1341 opened Jun 24, 2026 by JiaoliangYu Contributor • Draft
1 task
[gfx1151] Online INT8 W8A8 for Qwen3.6 27B / 35B-A3B on RDNA3.5, with working MTP
#1337 opened Jun 24, 2026 by carlushuang Collaborator Loading…
Feat/low bit ep
#1336 opened Jun 24, 2026 by JiaoliangYu Contributor • Draft
1 task
1
[atom][m3] enable m3 tbo
#1324 opened Jun 23, 2026 by zhuyuhua-v Collaborator • Draft
1 task
feat(openai): Qwen3 (qwen3_coder/qwen3_xml) tool-call support
#1319 opened Jun 23, 2026 by carlushuang Collaborator Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.