Default Branch

c7fc509417 · opencl: add F32-to-I32 ARGMAX (#30897) · Updated 2026-10-22 09:02:50 +08:00

Branches

e7fbfc9b80 · ci : tmp fixes · Updated 2026-02-11 21:48:40 +08:00    tqcq

3590
22

5372fc6461 · wip · Updated 2026-02-11 05:44:42 +08:00    tqcq

3555
18

b9b56b017e · Apply suggestion from @ggerganov (src->buffer to buf_src) v2 · Updated 2026-02-10 19:00:44 +08:00    tqcq

3504
13

5144018e7b · cont : simplify · Updated 2026-02-07 20:50:05 +08:00    tqcq

3525
4

1213a03564 · qwen3next : fix chunking · Updated 2026-02-04 16:06:38 +08:00    tqcq

3558
1

5b01d8575d · examples : add compare-mlx · Updated 2026-01-31 15:57:35 +08:00    tqcq

3595
1

6c8a04576e · experiments · Updated 2026-01-28 15:45:07 +08:00    tqcq

3646
29

8b407e3978 · quant : manual overrides of tensor types take precedence · Updated 2026-01-20 17:20:24 +08:00    tqcq

3710
1

3bfbbcc5fc · winget : update komac version · Updated 2026-01-18 16:29:03 +08:00    tqcq

3720
1

e2751545b9 · cont : inline verification · Updated 2026-01-17 20:33:07 +08:00    tqcq

3732
5

36f0132464 · CUDA: Factor out and re-use block_reduce function (#18785) · Updated 2026-01-15 10:44:54 +08:00    tqcq

3751
0
Included

60864997fe · fit-params : print signed int for -ngl param · Updated 2026-01-15 01:59:23 +08:00    tqcq

3754
1

08b5d956fc · minor : std::unordered_set over std::set · Updated 2026-01-12 19:35:25 +08:00    tqcq

3907
3

4a2751258a · server : simplify prompt state transition branches · Updated 2026-01-09 23:46:03 +08:00    tqcq

3806
11

caff0fd247 · server : adjust unified KV cache tests · Updated 2026-01-09 20:26:14 +08:00    tqcq

3806
1

0fca4308f7 · Initial plan · Updated 2026-01-08 23:16:59 +08:00    tqcq

3816
2

091d98e2c5 · rpc : use std::unique_ptr for the message_queue · Updated 2026-01-06 21:32:01 +08:00    tqcq

3855
2

54ccf2476b · ci : require editor config · Updated 2026-01-06 19:04:35 +08:00    tqcq

3847
1

4a95b44864 · alloc : skip unassigned leafs · Updated 2026-01-06 17:24:56 +08:00    tqcq

3847
1

bf3f12df4c · graph : constant topology for tokens/embeddings inputs · Updated 2026-01-02 21:46:45 +08:00    tqcq

3880
2