Default Branch

3125d79950 · [Chore] Remove unused PolyNorm layer (#27110) · Updated 2025-10-18 03:03:43 +08:00

Branches

b801bf30d7 · iterate · Updated 2025-06-29 06:21:17 +08:00

5172
2

e53382cc2e · Sage Moore fixes for full cuda graph support for DeepEP+DeepGEMM LL · Updated 2025-06-24 23:21:52 +08:00

5245
1

fcec8c8827 · add debug cruft · Updated 2025-06-21 04:37:37 +08:00

5332
12

e17250f0d2 · fix precommit · Updated 2025-06-19 12:17:43 +08:00

5319
1

b6553be1bc · [Misc] Slight improvement of the BNB (#19418) · Updated 2025-06-10 21:51:49 +08:00

5473
0
Included

ca15f0afe6 · ci(Mergify): configuration update · Updated 2025-06-09 15:44:44 +08:00

5504
1

d3b51c9bba · fix build · Updated 2025-06-09 08:38:37 +08:00

5749
10

9a76ef07b9 · Add pandas and datasets for benchmarks · Updated 2025-06-04 21:51:59 +08:00

5579
1

1236aebf0e · Merge remote-tracking branch 'origin/main' into fp8_ep_dp · Updated 2025-06-03 02:53:27 +08:00

5632
20

5fbbfe9a4c · [BugFix] FA2 MLA Accuracy Issue (#18807) · Updated 2025-05-30 23:50:58 +08:00

5747
1

2e773e55b3 · docs: merge v1 architecture with class hierarchy · Updated 2025-05-18 14:48:12 +08:00

5956
1

221118dc85 · [Bugfix] Use a different prompt for benchmark_serving.py test prompt · Updated 2025-05-18 02:36:31 +08:00

5957
1

f96a3cc713 · test · Updated 2025-05-10 04:31:08 +08:00

6141
2

79acf80471 · Fast decode prepare path for prepare_inputs logic · Updated 2025-05-09 01:26:00 +08:00

6405
1

bcf3c8230d · Merge branch 'main' into woosuk-jf · Updated 2025-05-05 02:16:07 +08:00

6249
3

b73fdb927a · draft · Updated 2025-05-04 01:50:34 +08:00

6400
1

3015d5634e · [BugFix][Attention] Fix sliding window attention in V1 giving incorrect results (#17574) · Updated 2025-05-03 02:02:48 +08:00

6396
3

a7b809e0f0 · Merge remote-tracking branch 'upstream/main' into benchmark-output · Updated 2025-04-23 22:55:50 +08:00

-1
-1

ec69124eb4 · [Misc] Improve readability of get_open_port function. (#17024) · Updated 2025-04-23 14:16:53 +08:00

6538
0
Included

161010c384 · Initial stubs for P/D scheduling changes · Updated 2025-04-19 04:42:49 +08:00

6616
1