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

e1a763558c · [CI] Discover Rust coverage artifacts from build metadata · 最后更新于 2026-07-23 06:44:16 +00:00    frostbyte_neo

666
7

a02155c787 · Merge branch 'main' into cuda-arch-fixup · 最后更新于 2026-07-21 01:33:48 +00:00    frostbyte_neo

688
11

1fbb5585a1 · use rustbin for vllm-rs binary · 最后更新于 2026-07-17 06:13:50 +00:00    frostbyte_neo

781
1

166a8e954b · [Model] Add Inkling multi-depth MTP support [5/N] · 最后更新于 2026-07-16 21:17:29 +00:00    frostbyte_neo

796
1

78e6067cf7 · [Distributed] Use NVSHMEM symm-mem backend across nodes · 最后更新于 2026-07-16 20:44:32 +00:00    frostbyte_neo

796
1

4b6b99b9ef · Bump protobuf from 6.33.6 to 7.35.1 · 最后更新于 2026-07-14 05:00:26 +00:00    frostbyte_neo

914
1

e898f259a3 · Bump fsspec from 2024.12.0 to 2026.6.0 · 最后更新于 2026-07-14 04:58:47 +00:00    frostbyte_neo

914
1

3a981fbbdb · fused padding to kernel · 最后更新于 2026-07-13 22:13:11 +00:00    frostbyte_neo

928
1

6bf03e0d95 · [Core] Add explicit layer parallel plans · 最后更新于 2026-07-13 19:12:30 +00:00    frostbyte_neo

952
1

a9ee5833ca · Merge branch 'main' into wentao-fix-es-v2-bug · 最后更新于 2026-07-13 18:19:23 +00:00    frostbyte_neo

930
8

69da6cc79f · Init · 最后更新于 2026-07-13 07:16:33 +00:00    frostbyte_neo

1008
1

752a3a5044 · [Bugfix] Guard mixed-dtype allreduce RMSNorm quant fusions (#48330) · 最后更新于 2026-07-12 23:40:12 +00:00    frostbyte_neo

1145
19

702f4814fe · [docs] Fix the docs build (#48008) · 最后更新于 2026-07-11 10:25:04 +00:00    frostbyte_neo

1145
17

62a0750892 · [Model] Add LongCat-2.0 (sparse attention, MTP, n-gram fixes) · 最后更新于 2026-07-11 02:12:49 +00:00    frostbyte_neo

987
1

0116e1cedc · [Core] Enable extensible KV cache for all attention backends and Mamba · 最后更新于 2026-07-11 00:08:34 +00:00    frostbyte_neo

1303
3

3ecf840f0f · Use PDL · 最后更新于 2026-07-10 15:17:05 +00:00    frostbyte_neo

993
30

e5588e49bc · [Core][KV events] Report prefix-cache-reused blocks in full report mode (#45261) · 最后更新于 2026-07-10 05:46:54 +00:00    frostbyte_neo

1006
0
已包含

cc934277a9 · Merge branch 'main' into woosuk/gumbel-fp32-rand64 · 最后更新于 2026-07-08 16:35:06 +00:00    frostbyte_neo

1054
6

30a3a7a7ff · [GLM 5.2] Integrate NVFP4 MegaMoE · 最后更新于 2026-07-07 17:37:10 +00:00    frostbyte_neo

1108
1

c716d13203 · add json passthrough support · 最后更新于 2026-07-07 03:28:29 +00:00    frostbyte_neo

1250
5