github-featured / vllm-project--vllm

分支列表

main

pre-commit / pre-run-check (push) Has been cancelled

pre-commit / pre-commit (push) Has been cancelled

46e6a83ce1 · [Bugfix][KV Offload] Clean up resources after initialization failure (#51227) · 最后更新于 2026-08-06 11:42:13 +00:00

remove-fp4-moe-env-var-clean ed05497d29 · Replace VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE env var with max_num_batched_tokens · 最后更新于 2026-03-20 01:23:05 +00:00 frostbyte_neo	4645 1	ZIP TAR.GZ
releases/v0.18.0 bcf2be9612 · [cherry-pick][Bugfix] Disable monolithic TRTLLM MoE for Renormalize routing (#37591)#37605 · 最后更新于 2026-03-19 22:06:38 +00:00 frostbyte_neo	4733 11	ZIP TAR.GZ
fix_nixl_triton_attn 3240a1e486 · Merge branch 'main' into fix_nixl_triton_attn · 最后更新于 2026-03-19 20:34:21 +00:00 frostbyte_neo	4579 4	ZIP TAR.GZ
prometheus-cudagraph-pct 119ccde424 · [Metrics] Add Prometheus counter for CUDA graph iteration mode · 最后更新于 2026-03-19 03:11:25 +00:00 frostbyte_neo	4621 1	ZIP TAR.GZ
khluu/cherrypick37322 f8430dc9d4 · p · 最后更新于 2026-03-18 08:46:31 +00:00 frostbyte_neo	4659 1	ZIP TAR.GZ
claude/optimize-weight-loading-7FlLd fadfefcc6e · feat: lazy TP weight loading via SafetensorsSlice · 最后更新于 2026-03-18 00:20:56 +00:00 frostbyte_neo	4673 1	ZIP TAR.GZ
gb200-0317 be441ac536 · zero out attn output · 最后更新于 2026-03-17 21:10:20 +00:00 frostbyte_neo	4679 4	ZIP TAR.GZ
claude/nervous-meitner 044d35c7f1 · Merge branch 'main' into claude/nervous-meitner · 最后更新于 2026-03-17 16:39:29 +00:00 frostbyte_neo	4689 3	ZIP TAR.GZ
mrv2-ci-test 95ef052724 · Merge branch 'main' into mrv2-ci-test · 最后更新于 2026-03-14 17:29:16 +00:00 frostbyte_neo	4789 2	ZIP TAR.GZ
tms/nvfp4-nan-contamination-test 8cb4e2a378 · [Test] Add NVFP4 scale padding contamination test for mm_fp4 · 最后更新于 2026-03-13 19:00:25 +00:00 frostbyte_neo	4853 3	ZIP TAR.GZ
zhuohan/remove-unnecessary-instance_id-setup 423ff4ebaa · Merge branch 'main' into zhuohan/remove-unnecessary-instance_id-setup · 最后更新于 2026-03-12 07:52:39 +00:00 frostbyte_neo	4860 2	ZIP TAR.GZ
woosuk/mrv2-cudagraph-attn-fix 7127e49d1c · [Model Runner V2] Introduce num_tokens_for_attn · 最后更新于 2026-03-11 19:47:58 +00:00 frostbyte_neo	4888 1	ZIP TAR.GZ
releases/v0.17.1 95c0f928cd · [NemotronH] Small fix reasoning parser (#36635) · 最后更新于 2026-03-11 09:51:18 +00:00 frostbyte_neo	5180 16	ZIP TAR.GZ
luka/fix-rms-quant-non-contiguous f247a5f37d · Add checks for hidden size and input stride divisibility by 4, remove opcheck from unit test & convert returns to skips · 最后更新于 2026-03-10 17:56:42 +00:00 frostbyte_neo	4959 8	ZIP TAR.GZ
cursor/main-branch-failure-triage-f8d5 6be833fe82 · Add Buildkite main branch failure triage script · 最后更新于 2026-03-10 02:28:07 +00:00 frostbyte_neo	4980 1	ZIP TAR.GZ
cursor/VLLM-94-usage-stats-v2-design-584f 89f6318db2 · docs: Add Usage Stats V2 PRD and initial design sketch (VLLM-94) · 最后更新于 2026-03-08 18:22:01 +00:00 frostbyte_neo	5029 1	ZIP TAR.GZ
vllm-dashboard 4b6ff605fc · update frontend · 最后更新于 2026-03-08 04:23:28 +00:00 frostbyte_neo	5042 16	ZIP TAR.GZ
fix/eplb-nvfp4-modelopt 36486dd057 · EPLB: add post-rearrangement weight invariant checks · 最后更新于 2026-03-07 22:44:53 +00:00 frostbyte_neo	5041 4	ZIP TAR.GZ
fix/eplb-prometheus-metrics da742158e1 · [Misc] Redesign EPLB Prometheus metrics for per-rank aggregation · 最后更新于 2026-03-07 19:51:41 +00:00 frostbyte_neo	5054 4	ZIP TAR.GZ
fix/eplb-debug-logging 0ccb2ef093 · [Misc] Add EPLB debug logging for balance diagnostics · 最后更新于 2026-03-07 03:20:28 +00:00 frostbyte_neo	5054 2	ZIP TAR.GZ

... 9 10 11 12 13 ...

默认分支

分支列表