Default Branch

main 8a81d776ce · Fix typo in ValueError message: use kv_role instead of kv_disagg_role (#27166) · Updated 2025-10-20 03:47:19 +08:00

ZIP  TAR.GZ

Branches

woosuk/rm-add-init-env 6f47333c4e · [Misc] Allow override VLLM_DISTRIBUTED_INIT_METHOD_OVERRIDE · Updated 2025-10-19 09:47:13 +08:00	9 1		ZIP  TAR.GZ
codex/add-1-option-for-max-model-length 14299bfcaf · Derive auto max model len state from original value · Updated 2025-10-19 02:49:36 +08:00	35 1		ZIP  TAR.GZ
zhuohan/moe-kernel-experiment dcf059ab84 · deepep HT dispatch no abstraction · Updated 2025-10-18 09:42:27 +08:00	237 6		ZIP  TAR.GZ
wentao-optimize-startup-log-2 99c02cce50 · update using local · Updated 2025-10-18 04:37:15 +08:00	33 9		ZIP  TAR.GZ
zhuohan/remove-virtual-engine a2599dca0f · fix missing removal · Updated 2025-10-18 02:35:42 +08:00	55 2		ZIP  TAR.GZ
wentao-fix-mypy-v1 3565e693c6 · Merge branch 'main' into wentao-fix-mypy-v1 · Updated 2025-10-18 00:53:05 +08:00	37 3		ZIP  TAR.GZ
woosuk/test-router 69c9a01538 · disable flashinfer warmup · Updated 2025-10-17 00:49:29 +08:00	108 4		ZIP  TAR.GZ
woosuk/router-nixl 01e389cd94 · fix · Updated 2025-10-17 00:48:51 +08:00	108 14		ZIP  TAR.GZ
moe_dual_stream 6f30ab9ab3 · [Performance] Run shared_experts on a separate cuda stream (in parallel with the FusedMoE) · Updated 2025-10-17 00:10:35 +08:00	86 1		ZIP  TAR.GZ
copilot/disable-batched-triton-kernel c72d44ba4a · Add test for batched triton fallback behavior · Updated 2025-10-16 11:46:02 +08:00	100 3		ZIP  TAR.GZ
update_from_kv_xfer_finished_race_fix 2797adb329 · cleanup · Updated 2025-10-16 02:07:49 +08:00	115 2		ZIP  TAR.GZ
releases/v0.11.1 c3a722fcb2 · [CI Failure] Fix tests with missing TinyLlama-1.1B-Chat-v1.0-FP8-e2e (#26816) · Updated 2025-10-15 02:38:59 +08:00	167 0	Included	ZIP  TAR.GZ
verbose-prime-rl-ci 38cf8237d4 · Fix pytest verbosity for prime-rl ci · Updated 2025-10-14 09:06:33 +08:00	205 1		ZIP  TAR.GZ
woosuk/remove-req-idx-mapping 22bf5c5077 · fix · Updated 2025-10-12 02:38:33 +08:00	251 4		ZIP  TAR.GZ
skip-lmfe-tests 37d0a00b16 · [CI] Skip lm-format-enforcer test cases · Updated 2025-10-11 03:14:25 +08:00    frozenleaves	269 1		ZIP  TAR.GZ
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    frozenleaves	668 34		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    frozenleaves	1206 8		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    frozenleaves	421 1		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    frozenleaves	937 454		ZIP  TAR.GZ
debug-logs 6f62c94d7e · updated · Updated 2025-10-04 01:47:16 +08:00    frozenleaves	491 2		ZIP  TAR.GZ