Skip to content

Pull requests: ROCm/vllm

New pull request New
43 Open 777 Closed
43 Open 777 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

[feat] Add ROCm ATOM model impl backend
#850 opened Dec 25, 2025 by zejunchen-zejun • Draft
Update unquantized_fused_moe_method.py
#849 opened Dec 24, 2025 by aaab8b Loading…
5 tasks
1
optimized dsv3.2 missing underscore
#847 opened Dec 18, 2025 by gronsti-amd Loading…
5 tasks
2
Add aiter qknorm and rope fusion kernel
#844 opened Dec 11, 2025 by kliuae-amd Loading…
5 tasks
Amd/deepseek aiter fusions
#842 opened Dec 8, 2025 by dllehr-amd • Draft
5 tasks
[Triton] Add Fused GEMM A8W8 + Split + Concat to Deepseek FP8 Model
#831 opened Dec 3, 2025 by farlukas • Draft
1 of 3 tasks
[Triton] add VLLM_ROCM_USE_AITER_TRITON_FUSED_GEMM_FP4_SPLIT_CAT
#827 opened Dec 2, 2025 by k50112113 Loading…
[bugfix mxpf4] Infer mxfp4 quantmethod from layer
#824 opened Nov 27, 2025 by ZhiweiYan-96 Loading…
5 tasks
2
[ROCm][MLA] Enable MLA persistent kernel with fp8 and bf16 support
#817 opened Nov 20, 2025 by zejunchen-zejun Loading…
3
[ROCm][FP4 BMM] integrate FP4 BMM
#816 opened Nov 20, 2025 by zejunchen-zejun Loading…
2
Add feature of hipBLASLt online tuning
#815 opened Nov 20, 2025 by hanlin12-AMD Loading…
5 tasks
1
[rocm]use aiter triton kernel as triton mha fallback path
#809 opened Nov 14, 2025 by zhuyuhua-v • Draft
1
[DO NOT MERGE]Enable FP4 bmm for k_up_proj and v_up_proj in MLA
#797 opened Nov 7, 2025 by ZhiweiYan-96 Loading…
5 tasks
enable sequence parallel for rocm
#790 opened Nov 5, 2025 by zhuyuhua-v Loading…
1
[Triton] add a16w8 gemm for DS-R1 for o_proj for decode, add rocm_aiter_triton…
#788 opened Nov 4, 2025 by k50112113 Loading…
[Triton] 355 wip Llama FP4 triton fusion + TP8 triton decode shape tunning
#783 opened Oct 31, 2025 by k50112113 Loading…
1
add aiter fusion pattern for sequence parallel
#781 opened Oct 31, 2025 by zhuyuhua-v • Draft
5 tasks
[MHA] add mha dispatch logic
#776 opened Oct 30, 2025 by gbyu-amd Loading…
5 tasks
Use UNIFORM QueryLen MLA for MTP
#773 opened Oct 29, 2025 by ZhiweiYan-96 Loading…
5 tasks
Streaming logic for fused_exports and MOE
#768 opened Oct 27, 2025 by omuhamma • Draft
5 tasks
@omuhamma
[ROCM] Llama4 VLLM_ROCM_USE_AITER_TRITON_FUSED_ROPE_ZEROS_KV_CACHE support
#763 opened Oct 24, 2025 by tpopp Loading…
Create determinism.md
#760 opened Oct 23, 2025 by shajrawi Loading…
[WIP] Support persistent MLA for ROCm MLA backend
#739 opened Oct 16, 2025 by ganyi1996ppo Loading…
5 tasks
2
Quick port of fp4 fusedmoe
#724 opened Sep 30, 2025 by jpvillam-amd Loading…
1
Add dispatch for different mha backend
#722 opened Sep 29, 2025 by zhuyuhua-v • Draft
5 tasks
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.