Skip to content

Pull requests: ROCm/vllm

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Support fp8 with static scales
#725 opened Oct 3, 2025 by lburzawa Loading…
5 tasks
Quick port of fp4 fusedmoe
#724 opened Sep 30, 2025 by jpvillam-amd Loading…
[Triton] Shaoclee/355 wip mha rope kv cache
#723 opened Sep 29, 2025 by k50112113 Loading…
Add dispatch for different mha backend
#722 opened Sep 29, 2025 by zhuyuhua-v Draft
5 tasks
Fix attn bug in qwen3-8b benchmark test
#721 opened Sep 28, 2025 by PerryZhang01 Loading…
5 tasks
update aiter fused_moe interface
#720 opened Sep 28, 2025 by zhiding512 Loading…
[FEAT] Add support for AITER bpreshuffle block scale gemm
#717 opened Sep 27, 2025 by tjtanaavllm Loading…
5 tasks
[Perf] refactor attention backend for perf boost
#713 opened Sep 26, 2025 by ganyi1996ppo Loading…
5 tasks
add hipblas in Docker build
#708 opened Sep 25, 2025 by dllehr-amd Loading…
5 tasks
[ROCm] Add allreduce dispatcher for ROCm device
#704 opened Sep 24, 2025 by zejunchen-zejun Loading…
Qwen-next script
#702 opened Sep 24, 2025 by ZhiweiYan-96 Loading…
5 tasks
support rocblas for rocm_unquantized_gemm
#665 opened Sep 10, 2025 by eliotwang Loading…
Add cache config for gpt oss
#656 opened Sep 5, 2025 by cagrikymk Draft
fix flashmla metadata build calls()
#636 opened Aug 19, 2025 by ZJLi2013 Loading…
[Model] Add GPT-OSS model code and config
#625 opened Aug 7, 2025 by ashishtanwer Loading…
add Fused_rms_quant for deepseek_v2 model
#611 opened Jul 29, 2025 by ZJLi2013 Loading…
add fused fp8 bmm
#604 opened Jul 25, 2025 by k50112113 Loading…
ProTip! Updated in the last three days: updated:>2025-10-02.