分支列表

默认分支

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

分支列表

8ae4f9223e · p · 最后更新于 2026-05-01 22:02:51 +00:00    frostbyte_neo

3519
27

67c74e5980 · p · 最后更新于 2026-05-01 21:47:49 +00:00    frostbyte_neo

3519
28

797cdc15f0 · [CI] Use uv-installed standalone Python in vllm-base (drop deadsnakes) · 最后更新于 2026-05-01 20:42:32 +00:00    frostbyte_neo

3519
28

77230471c0 · remove torch 2.9, 2.10 workround · 最后更新于 2026-04-30 21:10:50 +00:00    frostbyte_neo

3399
1

858ce2a1a0 · Adjust B200 k8s CI job coverage · 最后更新于 2026-04-30 09:06:40 +00:00    frostbyte_neo

3432
1

6841f5dc77 · [ROCm] Add env flags to disable dynamic MXFP4 quant and enable AITER tuned GEMMs for Attention Projection Layers (#39987) · 最后更新于 2026-04-29 23:07:46 +00:00    frostbyte_neo

3424
0
已包含

bdb3b45e02 · Apply suggestion from @ProExpertProg · 最后更新于 2026-04-29 20:03:22 +00:00    frostbyte_neo

3435
3

b65206a9c0 · Add sp_min_token_num=0 to E2E correctness tests for SP and AsyncTP · 最后更新于 2026-04-29 18:11:22 +00:00    frostbyte_neo

3435
1

71475ffb12 · Revert "[Not to Main] Docker Release Mooncake Deps (#159)" · 最后更新于 2026-04-29 08:22:29 +00:00    frostbyte_neo

3461
7

d423438f1b · reuse cuda major · 最后更新于 2026-04-28 13:36:59 +00:00    frostbyte_neo

3503
2

e0dd86f6c3 · deprecate timeout · 最后更新于 2026-04-28 07:03:27 +00:00    frostbyte_neo

3503
2

88d34c6409 · [Docker] Install numactl CLI in CUDA runtime image (#41032) · 最后更新于 2026-04-27 19:04:32 +00:00    frostbyte_neo

3519
4

5c7ecf1586 · Support topk 1024 · 最后更新于 2026-04-26 17:34:44 +00:00    frostbyte_neo

3523
21

8a77e75e01 · fix: add platform guards for tilelang in mhc.py and fix test imports · 最后更新于 2026-04-25 17:29:00 +00:00    frostbyte_neo

3530
6

29798c29fb · Fixes for Triton implementations · 最后更新于 2026-04-25 15:27:12 +00:00    frostbyte_neo

3808
1

931b3f6110 · Done · 最后更新于 2026-04-25 13:23:05 +00:00    frostbyte_neo

3529
1

8c44bbfb7f · Merge branch 'main' into wentao-optimize-pooling-by-ragged-tensor · 最后更新于 2026-04-23 20:14:23 +00:00    frostbyte_neo

3577
7

cb68c1a314 · Fix ci · 最后更新于 2026-04-22 18:26:48 +00:00    frostbyte_neo

3615
1

b547993038 · type ignore · 最后更新于 2026-04-21 19:06:50 +00:00    frostbyte_neo

3647
3

245aa274aa · Disable Triton wrap by default, only enable in lowering pass · 最后更新于 2026-04-20 19:36:27 +00:00    frostbyte_neo

3808
10