Default Branch

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

Branches

dc1b4a6f13 · [Core][V0] Enable regex support with xgrammar (#13228) · Updated 2025-04-14 10:13:38 +08:00

6705
0
Included

ccd21e1993 · [V1] Fix profiling.py · Updated 2025-04-12 02:36:37 +08:00

6734
1

87e47eb1db · Fix use_ep · Updated 2025-04-08 03:56:41 +08:00

6844
1

6de0982dd0 · added · Updated 2025-04-06 22:07:43 +08:00

-1
-1

296c6572dd · Revert "[V1] DP scale-out (1/N): Use zmq ROUTER/DEALER sockets for input queue (#15906)" · Updated 2025-04-06 12:10:57 +08:00

6884
2

d3eddd6ef1 · initial · Updated 2025-04-02 07:06:59 +08:00

6958
1

af985d70bf · change to greedy · Updated 2025-04-02 06:53:26 +08:00

6996
7

db9dfcfa6a · [Docs] Add Ollama meetup slides (#15905) · Updated 2025-04-02 04:58:59 +08:00

6954
0
Included

4c42267293 · updated · Updated 2025-03-28 10:26:20 +08:00

-1
-1

44d638a896 · merge · Updated 2025-03-26 01:26:20 +08:00

-1
-1

25f560a62c · [V1][Spec Decode] Update target_logits in place for rejection sampling (#15427) · Updated 2025-03-25 12:04:41 +08:00

7142
0
Included

220d694080 · updated · Updated 2025-03-24 09:00:20 +08:00

-1
-1

8db54c7912 · Merge branch 'main' into v1-sched-interface-2 · Updated 2025-03-21 08:56:13 +08:00

7224
17

61c7a1b856 · [V1] Minor V1 async engine test refactor (#15075) · Updated 2025-03-20 01:37:17 +08:00

7257
0
Included

966f933ee1 · [Bugfix] Fix LoRA extra vocab size (#15047) · Updated 2025-03-19 01:51:10 +08:00

7298
9

031c8b32a4 · Add time comment · Updated 2025-03-17 21:50:44 +08:00

7303
4

90eb28ca21 · [V1][Scheduler] Use dict for running queue · Updated 2025-03-14 04:11:07 +08:00

7399
1

bfff9bcd1d · [V1] TPU - Remove self.kv_caches · Updated 2025-03-06 04:42:05 +08:00

7582
1

3679753af5 · Reduce Scatter Plumbing · Updated 2025-03-01 00:33:52 +08:00

7660
1

34e3494e70 · Fix failing MyGemma2Embedding test (#13820) · Updated 2025-02-26 04:33:03 +08:00

7720
0
Included