Default Branch

3fc4e10527 · sched : reintroduce less synchronizations during split compute (#20793) · Updated 2026-06-26 14:18:30 +00:00

Branches

715ed28683 · use scalar sums · Updated 2026-03-07 21:11:40 +00:00    kanshan

1573
3

121fe62182 · test · Updated 2026-03-06 14:30:32 +00:00    kanshan

1589
7

4b436e4e5e · flake8 fix · Updated 2026-02-23 10:48:01 +00:00    kanshan

1697
20

5d45884106 · metal : fix build · Updated 2026-02-18 07:14:31 +00:00    kanshan

1819
23

5da56dc1d8 · args : add -kvu to llama-parallel · Updated 2026-02-12 19:50:01 +00:00    kanshan

1819
17

e7fbfc9b80 · ci : tmp fixes · Updated 2026-02-11 13:48:40 +00:00    kanshan

1869
22

5372fc6461 · wip · Updated 2026-02-10 21:44:42 +00:00    kanshan

1834
18

b9b56b017e · Apply suggestion from @ggerganov (src->buffer to buf_src) v2 · Updated 2026-02-10 11:00:44 +00:00    kanshan

1834
13

5144018e7b · cont : simplify · Updated 2026-02-07 12:50:05 +00:00    kanshan

1855
4

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

1888
1

5b01d8575d · examples : add compare-mlx · Updated 2026-01-31 07:57:35 +00:00    kanshan

1925
1

6c8a04576e · experiments · Updated 2026-01-28 07:45:07 +00:00    kanshan

1976
29

8b407e3978 · quant : manual overrides of tensor types take precedence · Updated 2026-01-20 09:20:24 +00:00    kanshan

2040
1

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

2050
1

e2751545b9 · cont : inline verification · Updated 2026-01-17 12:33:07 +00:00    kanshan

2062
5

36f0132464 · CUDA: Factor out and re-use block_reduce function (#18785) · Updated 2026-01-15 02:44:54 +00:00    kanshan

2081
0
Included

60864997fe · fit-params : print signed int for -ngl param · Updated 2026-01-14 17:59:23 +00:00    kanshan

2084
1

08b5d956fc · minor : std::unordered_set over std::set · Updated 2026-01-12 11:35:25 +00:00    kanshan

2237
3

4a2751258a · server : simplify prompt state transition branches · Updated 2026-01-09 15:46:03 +00:00    kanshan

2136
11

caff0fd247 · server : adjust unified KV cache tests · Updated 2026-01-09 12:26:14 +00:00    kanshan

2136
1