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

6257a61c3d · Merge branch 'main' into worktree-fix-cudagraph-flaky · 最后更新于 2026-07-06 17:59:00 +00:00    frostbyte_neo

1168
2

2e7e11b6f8 · sleep metrics · 最后更新于 2026-07-06 13:09:56 +00:00    frostbyte_neo

1255
3

6099f540ae · Handle older FlashInfer FP8 MoE signatures · 最后更新于 2026-07-05 02:00:30 +00:00    frostbyte_neo

1221
1

79b560e29a · Fix DeepSeek V4 SM10 sparse MLA default · 最后更新于 2026-07-05 01:59:07 +00:00    frostbyte_neo

1221
1

f67c1ad263 · FIX · 最后更新于 2026-07-04 13:45:35 +00:00    frostbyte_neo

1250
4

0263839f85 · Init · 最后更新于 2026-07-03 00:17:18 +00:00    frostbyte_neo

1284
1

9feb5a94be · [Spec Decode] Keep draft_gumbel_pos at the top of spec_decode utils · 最后更新于 2026-07-02 15:56:23 +00:00    frostbyte_neo

1280
5

ce89bc6358 · update · 最后更新于 2026-07-02 15:16:21 +00:00    frostbyte_neo

1306
3

6e714a103c · stash · 最后更新于 2026-07-02 05:51:48 +00:00    frostbyte_neo

1313
2

b31b57a391 · [ZenCPU] Changes with respect to relevant cpu tests for ZenDNN · 最后更新于 2026-06-30 15:49:40 +00:00    frostbyte_neo

1369
1

95dcefaaa5 · Bump actions/setup-python from 6.1.0 to 6.3.0 · 最后更新于 2026-06-30 12:18:49 +00:00    frostbyte_neo

1386
1

61b40475c7 · [Rust Frontend] Tolerate out-of-vocab tokens from prompt in detokenizer · 最后更新于 2026-06-30 07:37:56 +00:00    frostbyte_neo

1401
8

d39a646401 · Add Triton warmup compile-key tracing · 最后更新于 2026-06-29 21:01:44 +00:00    frostbyte_neo

1428
1

2b30cdf9f4 · [CI/Build] Fix structural tag test for xgrammar 0.2.3 · 最后更新于 2026-06-29 19:51:51 +00:00    frostbyte_neo

1454
1

b35b9cf446 · wip · 最后更新于 2026-06-29 18:15:10 +00:00    frostbyte_neo

1455
1

ee0da84ab9 · [KV-Offloading] Fix tensors_per_block stride (#46888) · 最后更新于 2026-06-28 07:04:08 +00:00    frostbyte_neo

1704
18

3ef4bae91c · [Kernel] Manual activation+quant fusion via QuantizedActivation (Llama) · 最后更新于 2026-06-26 19:15:14 +00:00    frostbyte_neo

1515
1

8b00f41237 · [MiniMax-M3] Retune decode indexer launch grid for occupancy (#130) · 最后更新于 2026-06-25 18:14:52 +00:00    frostbyte_neo

1796
20

fb9f5790bb · megamoe · 最后更新于 2026-06-22 23:59:53 +00:00    frostbyte_neo

1767
16

dd54d6bc9d · Merge branch 'main' into wentao-fix-v2-mrope · 最后更新于 2026-06-22 22:26:56 +00:00    frostbyte_neo

1724
3