Default Branch

main 9e0726e5bf · [Meta] Official Eagle mm support, first enablement on llama4 (#20788) · Updated 2025-08-01 01:35:07 +08:00

ZIP  TAR.GZ

Branches

Search

triton-configs 9d762c3aa5 · updated · Updated 2025-07-15 10:09:43 +08:00	503 5		ZIP  TAR.GZ
tms/dp_cuda_visible_devices_fix 6bad110640 · add VLLM_VISIBLE_DEVICES · Updated 2025-07-14 10:06:20 +08:00	499 2		ZIP  TAR.GZ
fused-moe-tuning-ep 94e7c6dac7 · updated · Updated 2025-07-13 06:38:42 +08:00	511 5		ZIP  TAR.GZ
mla_decode_any_head 32e4481626 · [Attention] MLA - cutlass decode with unresticted num_heads · Updated 2025-07-12 01:37:33 +08:00	535 1		ZIP  TAR.GZ
gpu_ids2 ab153be252 · take 2 · Updated 2025-07-11 22:42:44 +08:00	564 1		ZIP  TAR.GZ
nixl-debug-oh-fixed 45c02abd72 · updated · Updated 2025-07-11 08:57:50 +08:00	995 37		ZIP  TAR.GZ
gpu-ids 37cf1f27f2 · hack 2 · Updated 2025-07-11 06:56:08 +08:00	602 6		ZIP  TAR.GZ
fix-doc-build 1db4b78a13 · Mock gguf in doc build · Updated 2025-07-11 04:39:35 +08:00	559 1		ZIP  TAR.GZ
dockerfile-nvcc-compress 9e011d3954 · Update mistaken usage of GREATER to GREATER_EQUAL · Updated 2025-07-10 01:41:55 +08:00	601 5		ZIP  TAR.GZ
add-python-3.13 b2bb4e34f3 · Merge branch 'main' into add-python-3.13 · Updated 2025-07-08 09:34:08 +08:00	646 7		ZIP  TAR.GZ
releases/v0.9.2 a5dd03c1eb · Revert "[V0 deprecation] Remove V0 CPU/XPU/TPU backends (#20412)" · Updated 2025-07-07 05:02:36 +08:00	672 1		ZIP  TAR.GZ
topk_id_hack 8209f9057d · i honestly can't believe i spelled it that way · Updated 2025-07-05 03:14:03 +08:00	693 3		ZIP  TAR.GZ
add-utils 7d092fc32c · revert skip-merge-desc · Updated 2025-07-04 04:30:45 +08:00    vLLM	714 3		ZIP  TAR.GZ
minus_x f8768f5244 · Remove executable flag on a few files · Updated 2025-07-02 21:58:53 +08:00    vLLM	742 1		ZIP  TAR.GZ
woosuk/simple-cuda-graph 8d6f411247 · fix · Updated 2025-07-02 02:24:59 +08:00    vLLM	767 2		ZIP  TAR.GZ
acc-rate 17bccecb1c · add mtbench dataste · Updated 2025-06-30 13:30:12 +08:00    vLLM	2051 2		ZIP  TAR.GZ
gemma3n-mm b801bf30d7 · iterate · Updated 2025-06-29 06:21:17 +08:00    vLLM	823 2		ZIP  TAR.GZ
deep_full_cudagraph_fix e53382cc2e · Sage Moore fixes for full cuda graph support for DeepEP+DeepGEMM LL · Updated 2025-06-24 23:21:52 +08:00    vLLM	896 1		ZIP  TAR.GZ
deepep_tweaks fcec8c8827 · add debug cruft · Updated 2025-06-21 04:37:37 +08:00    vLLM	983 12		ZIP  TAR.GZ
woosuk/cache-model-info 86bfededba · [Do not merge] Cache model info · Updated 2025-06-19 13:31:33 +08:00    vLLM	967 1		ZIP  TAR.GZ