Default Branch

4765f0f189 · [Bugfix] Fix sequence_parallel_chunk_impl custom op aliasing its input (#44130) · Updated 2026-06-05 23:56:36 +00:00

Branches

c27bdfa1a4 · fix mrv2 mm lora · Updated 2026-06-03 21:13:04 +00:00

82
1

b0ed553028 · [Distributed] Add UCX one-shot AllReduce for DP metadata sync · Updated 2026-06-03 19:46:10 +00:00

84
1

1aa72fa613 · Merge branch 'main' into wentao-fix-NixlConnector-PD-+-Spec-Decode-acceptance-(2-GPUs) · Updated 2026-06-03 18:14:26 +00:00

87
6

c545592816 · Merge branch 'main' into wentao-mrv2-migration-moe · Updated 2026-06-03 14:19:23 +00:00

96
5

1e79ce0db2 · Bump pyrate-limiter from 3.7.0 to 4.2.0 · Updated 2026-06-02 18:36:37 +00:00

135
1

fcfc38d144 · Bump fsspec from 2024.12.0 to 2026.4.0 · Updated 2026-06-02 18:31:55 +00:00

135
1

f36d57ec34 · Bump actions/setup-python from 6.1.0 to 6.2.0 · Updated 2026-06-02 18:31:03 +00:00

135
1

5f4d1774e9 · Bump actions/checkout from 6.0.1 to 6.0.3 · Updated 2026-06-02 18:29:39 +00:00

135
1

afcb580715 · [BugFix] Fix Humming MoE deploy error (#43100) · Updated 2026-06-02 16:32:50 +00:00

140
0
Included

a491f6dbca · [Cleanup] Remove graph break in sparse indexer · Updated 2026-06-02 16:13:59 +00:00

142
1

902f2978ba · Merge branch 'main' into wosouk/dsv4-attn-cleanup-2 · Updated 2026-06-02 03:32:33 +00:00

175
5

1ff2b11e17 · [DSv4] Refactor DeepseekV4Attention · Updated 2026-06-01 23:27:28 +00:00

185
2

1c65086cf4 · benchmark changes · Updated 2026-06-01 04:34:31 +00:00

689
2

f8d7bbf281 · minor · Updated 2026-05-30 16:52:49 +00:00

207
2

b1d07cbea5 · Merge branch 'main' into wentao-mrv2-migration-more-dense · Updated 2026-05-30 14:36:26 +00:00

208
14

8ad3817a8c · Revert "[ROCm][Perf] Support N=5 in wvSplitK skinny GEMM kernels for speculat…" · Updated 2026-05-29 16:25:29 +00:00

234
1

0b3ba88f16 · Revert "[CPU] Experimentally enable Triton and MRV2 (#43225)" · Updated 2026-05-29 09:28:43 +00:00

386
19

7e07848d50 · test: touch llama.py for coverage comparison · Updated 2026-05-28 20:33:50 +00:00

273
1

d4518933de · test: touch triton_reshape_and_cache_flash.py for coverage comparison · Updated 2026-05-28 20:33:44 +00:00

273
1

27075fc066 · test: touch jais.py for coverage comparison · Updated 2026-05-28 20:33:42 +00:00

273
1