Default Branch

8f8819795f · Fixing CI (#3184) · Updated 2025-04-18 11:07:18 +00:00

Branches

b86919a87a · fixes · Updated 2025-04-19 10:26:56 +00:00

3
4

2a10a28d08 · force attn to flashdecoding · Updated 2025-04-11 15:24:12 +00:00

0
5

3d71c06aff · flashinfer: head_dim -> head_dim_qk · Updated 2025-04-11 12:38:17 +00:00

0
2

dd187d2350 · wip(ci): debug the ci · Updated 2025-04-10 15:17:16 +00:00

0
10

73d0876f12 · Fixing the updating logic of backends. · Updated 2025-04-10 09:04:03 +00:00

97
8

d93ad244a3 · add attn · Updated 2025-04-09 16:37:34 +00:00

1
1

e5618d6e40 · add chunked attn support · Updated 2025-04-09 16:36:06 +00:00

1
1

a1f3ebe17c · Release 3.2.3 · Updated 2025-04-08 08:17:51 +00:00

2
1

c67546fd40 · Release 3.2.2 · Updated 2025-04-06 09:40:52 +00:00

7
1

53567b0028 · remove tr version · Updated 2025-04-05 19:57:36 +00:00

15
13

bfcc1df91f · test_kernel · Updated 2025-03-28 16:17:13 +00:00

2
3

cee44bff7a · Improve message to be useful without spans · Updated 2025-03-24 15:01:30 +00:00

2
1

e721574729 · fix: update test for tool_call_id in Message · Updated 2025-03-21 15:15:32 +00:00

3
3

65c6008847 · fix: bump openapi doc with new grammar option · Updated 2025-03-21 15:14:56 +00:00

3
8

69936732eb · feat: allow model load and stub logits · Updated 2025-03-19 19:55:19 +00:00

5
1

4d28897b4e · Fix release nix workflow. · Updated 2025-03-18 14:27:48 +00:00

6
2

e0535a13c5 · increase timeouts · Updated 2025-03-17 16:56:57 +00:00

13
11

73ee7837b8 · Update to kernels 0.2.0. · Updated 2025-03-13 09:30:07 +00:00

19
1

411a28288d · Release 3.2.0 · Updated 2025-03-12 10:15:49 +00:00

19
1

d4c6faa67b · Try to fix on main CI color. (#3101) · Updated 2025-03-12 09:12:24 +00:00

19
0
Included