Skip to content

Pull requests: ROCm/vllm

New pull request New
41 Open 1,134 Closed
41 Open 1,134 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

ci: bump build-rocm-wheels to torch 2.13, fix stale-line version resolution
#1237 opened Aug 21, 2026 by marcusr-amd Loading…
Update Dockerfile.rocm_base
#1224 opened Aug 19, 2026 by jvadakat Loading…
5 tasks
rocm: implement tie_weights for the dynamic INT8 lm_head
#1213 opened Aug 18, 2026 by roberteg16 • Draft
3 tasks done
[perf]: fuse forward_static() RoPE fallback ops via torch.compile
#1212 opened Aug 18, 2026 by serged-amd Loading…
4
[ROCm][Attention] Wide MHA decode attention kernel for gfx1151
#1087 opened Aug 12, 2026 by roberteg16 • Draft
5 of 6 tasks
[Model] Complete port of Transformers v5 heterogeneous config fix
#1086 opened Aug 11, 2026 by amd-callumm • Draft
1
[ROCm] Stop ROCPROFILER_REGISTER_LIBRARY leaking into engine subprocesses
#1077 opened Aug 3, 2026 by roberteg16 • Draft
5 tasks done
4
[bench] vit_attention: model-matching V stride + controllable cache-eviction (--flush-mib)
#1070 opened Jul 30, 2026 by parthash0804 Loading…
1
[ROCm][Kernel] W4A16 MoE prefill: M-aware moe_align block size (1.6x TTFT)
#1069 opened Jul 29, 2026 by stoivonen-amd • Draft
3 of 5 tasks
1
Release/0.23.0
#1058 opened Jul 14, 2026 by kiran-thumma Collaborator • Draft
5 tasks
[ROCm][Kernel] W4A16 skinny GEMM: hand-asm kernel for gfx1151
#1045 opened Jul 1, 2026 by mgehre-amd • Draft
[CI] Re-enable performance test job
#1033 opened Jun 29, 2026 by marcusr-amd • Draft
5 tasks
1
[ROCm] Split skinny_gemms_int8.cu into per-N translation units
#1028 opened Jun 26, 2026 by marcusr-amd • Draft
3 of 5 tasks
1
tune Qwen3-VL-4B prefill unified-attention on gfx1150
#1024 opened Jun 26, 2026 by qingxuamd Loading…
Fix GLM 5.2 mxfp4 MTP loading issue
#1022 opened Jun 25, 2026 by amd-xiaoyu12 Loading…
[ROCm][MoE] W4A16 MoE routing-distribution benchmark suite for the gfx11 prefill GEMM
#1020 opened Jun 25, 2026 by roberteg16 • Draft
455 war room findings
#1001 opened Jun 12, 2026 by jpvillam-amd Loading…
@jpvillam-amd
MoE: Grouped Triton GEMM for TTFT improvements
#970 opened May 26, 2026 by mgehre-amd • Draft
feat: Add NPU+GPU async pipelining for vision-language models
#936 opened May 14, 2026 by liangliangchang • Draft
4 of 5 tasks
10
Hybrid
#918 opened May 4, 2026 by liangliangchang • Draft
5 tasks
1
Auto-build flash-attn wheels on push, upload to S3
#910 opened Apr 30, 2026 by mgehre-amd • Draft
1 task
[ROCm][DSv4] Share AITER decode dequant + fp8-cast buffers across layers (rebased, stacked on #902)
#903 opened Apr 27, 2026 by ChuanLi1101 • Draft
2 of 4 tasks
4
[ROCm][DSv4] Make AITER sparse decode cudagraph-clean (rebased, stacked on #901)
#902 opened Apr 27, 2026 by ChuanLi1101 • Draft
2 of 5 tasks
5
[ROCm][DSv4] AITER-accelerated MLA decode for DeepSeek V4 on MI355X (rebased on tj/dsv4prrebase)
#901 opened Apr 27, 2026 by ChuanLi1101 • Draft
1 of 4 tasks
5
[Do Not Merge] For review purpose: Rocm/aiter mla dsv4 decode cudagraph
#900 opened Apr 26, 2026 by tjtanaavllm • Draft
5 tasks
ProTip! Mix and match filters to narrow down what you’re looking for.