Default Branch

288cc6c234 · [Attention] MLA with chunked prefill (#12639) · Updated 2025-02-22 07:30:12 +08:00

Branches

01c4dc8556 · minor · Updated 2025-02-22 09:22:59 +08:00

0
3

afa691378a · p · Updated 2025-02-22 08:22:12 +08:00

17
8

80ba19d5b1 · updated · Updated 2025-02-22 03:46:51 +08:00

1
1

476352aaa6 · p · Updated 2025-02-21 18:21:41 +08:00

2
1

d1b76c2a52 · Merge branch 'main' into update-torch-2.6.0 · Updated 2025-02-21 05:16:17 +08:00

15
12

5a7e9e2917 · p · Updated 2025-02-21 02:15:30 +08:00

17
1

01649f9661 · [V1] TPU - Add tensor parallel support via Ray · Updated 2025-02-21 00:43:40 +08:00

62
1

50f73aa235 · fix req-test · Updated 2025-02-20 17:28:01 +08:00

28
3

59ee7c7bbd · p · Updated 2025-02-20 15:47:46 +08:00

36
2

0d243f2a54 · [ROCm][MoE] mi300 mixtral8x7B perf for specific BS (#13577) · Updated 2025-02-20 12:01:02 +08:00

31
0
Included

0d243f2a54 · [ROCm][MoE] mi300 mixtral8x7B perf for specific BS (#13577) · Updated 2025-02-20 12:01:02 +08:00

31
0
Included

fec86c299c · Merge branch 'main' into add-python-3.13 · Updated 2025-02-18 04:26:38 +08:00

84
3

3dbd544c4e · Update add_label_precommit.yml · Updated 2025-02-14 06:23:29 +08:00

148
2

e79013b688 · merge with main · Updated 2025-02-14 06:08:52 +08:00

148
6

243408b6b4 · Support moe_wna16 as well · Updated 2025-02-13 03:18:29 +08:00

172
4

16e31b44c2 · wip · Updated 2025-02-12 13:01:24 +08:00

193
1

d0a8d15382 · p · Updated 2025-02-12 05:45:49 +08:00

224
7

fea0b1ea2d · [V1] Allow sliding window + prefix caching · Updated 2025-02-11 10:26:52 +08:00

212
1

70b4e46e70 · compilation is fixed · Updated 2025-02-07 04:49:29 +08:00

438
14

631ec50e84 · tmp · Updated 2025-02-05 10:28:52 +08:00

301
1