Default Branch

main 36960501d3 · [Hardware][Powerpc] Fix VLLM_CPU_OMP_THREADS_BIND="auto" low CPU utilization for Power (#27734) · Updated 2025-10-31 15:45:26 +08:00

ZIP  TAR.GZ

Branches

releases/v0.11.0 b8b302cde4 · Update CUDA architecture list in build pipeline for 12.9.1 wheels (#26592) · Updated 2025-10-11 02:15:45 +08:00    youngkingdom	953 34	Compare	ZIP  TAR.GZ
releases/v0.10.2 01efc7ef78 · [ci] fix wheel names for arm wheels (#24898) · Updated 2025-10-08 04:40:13 +08:00    youngkingdom	1491 8	Compare	ZIP  TAR.GZ
codex/remove-vllm-v0-engine-references-from-docs 944913c0fa · docs: clarify remaining v0 references · Updated 2025-10-07 01:59:13 +08:00    youngkingdom	706 1	Compare	ZIP  TAR.GZ
wye-refactor-w8a8-quant 920db41128 · [Quantization/NVFP4] Speed up TRTLLM NVFP4 MOE weight loading and fix K/V scale loading for MLA Attn (#25968) · Updated 2025-10-04 04:35:58 +08:00    youngkingdom	1222 454	Compare	ZIP  TAR.GZ
debug-logs 6f62c94d7e · updated · Updated 2025-10-04 01:47:16 +08:00    youngkingdom	776 2	Compare	ZIP  TAR.GZ
use-uv-python-for-docker 728c365e4d · Use uv to install python in Dockerfile · Updated 2025-10-02 23:05:47 +08:00    youngkingdom	826 1	Compare	ZIP  TAR.GZ
simon-mo-patch-1 eca0895879 · [Build] Update build image to ubuntu 22 · Updated 2025-10-02 13:25:12 +08:00    youngkingdom	828 1	Compare	ZIP  TAR.GZ
fix_ds_eagle 9ffb182ba3 · Fix config passed to deepseek_eagle · Updated 2025-09-30 21:03:27 +08:00    youngkingdom	874 1	Compare	ZIP  TAR.GZ
maybe_fix_hang_2 cd3ea013d6 · maybe fix · Updated 2025-09-28 08:49:34 +08:00    youngkingdom	919 1	Compare	ZIP  TAR.GZ
fix_hang 562107efb1 · Merge branch 'main' into fix_hang · Updated 2025-09-27 22:44:26 +08:00    youngkingdom	926 3	Compare	ZIP  TAR.GZ
dbo-cudagraph-size-cherry a4516dc190 · Merge branch 'main' of https://github.com/neuralmagic/vllm into sage/dbo-cudagraph-size · Updated 2025-09-27 04:45:41 +08:00    youngkingdom	949 3	Compare	ZIP  TAR.GZ
lwilkinson/cg-support ebfce922f9 · full cg support · Updated 2025-09-27 03:51:46 +08:00    youngkingdom	953 1	Compare	ZIP  TAR.GZ
lwilkinson/potential-cutlass-mla-fix db77f9b3a2 · potential hang fix · Updated 2025-09-27 01:24:13 +08:00    youngkingdom	954 1	Compare	ZIP  TAR.GZ
avoid-double-free 4a0d6ac40b · updated · Updated 2025-09-25 02:41:00 +08:00    youngkingdom	1034 1	Compare	ZIP  TAR.GZ
support_global_dp_logging 98d535eb4f · add aggregator interface and abstract common logic · Updated 2025-09-23 04:00:53 +08:00    youngkingdom	1256 2	Compare	ZIP  TAR.GZ
khluu/test_latest_feat 8db2939289 · [KV offload][5/N] Add CPUOffloadingSpec (#24251) · Updated 2025-09-23 03:30:36 +08:00    youngkingdom	1139 0	Included	ZIP  TAR.GZ
woosuk/fix-graph-pool 936da0f740 · update · Updated 2025-09-20 07:30:15 +08:00    youngkingdom	1208 2	Compare	ZIP  TAR.GZ
codex/remove-raydistributedexecutor-from-v0-engine 85013bf094 · Prune Ray v1 non-SPMD code paths · Updated 2025-09-19 11:42:46 +08:00    youngkingdom	1250 2	Compare	ZIP  TAR.GZ
amd_mori 9fac6aa30b · [BugFix] Fix DeepGEMM warmup, no m.weight_scale_inv (#25206) · Updated 2025-09-19 05:26:28 +08:00    youngkingdom	1250 0	Included	ZIP  TAR.GZ
woosuk/minor-worker-fix 2705f03cad · [Chore] Minor simplification for GPU worker · Updated 2025-09-19 03:40:34 +08:00    youngkingdom	1254 1	Compare	ZIP  TAR.GZ