Default Branch

76a5bc86d1 · common : use fs::path for cache dirs (#29595) · Updated 2026-09-29 00:24:03 -05:00

Branches

91c453fb11 · One cannot possibly be defining static_assert in a C++ compilation · Updated 2024-02-05 05:22:14 -06:00    upstream-archive

9179
2

49a483e0f2 · wip · Updated 2024-02-04 04:34:36 -06:00    upstream-archive

9205
60

a647257b47 · cuda : express strides with helper constants · Updated 2024-02-04 03:45:26 -06:00    upstream-archive

9205
60

b957b8f5f6 · cuda : add flash_attn kernel (wip) · Updated 2024-02-01 11:49:57 -06:00    upstream-archive

9209
39

ac26f27028 · cuda : increase C to 128 for better performance · Updated 2024-02-01 09:08:29 -06:00    upstream-archive

9209
61

1ad42b1f1e · ggml : ggml_soft_max uses F16 mask · Updated 2024-01-31 12:33:59 -06:00    upstream-archive

9209
36

719a087138 · iq3_xxs: forgotten update of the grid points · Updated 2024-01-30 10:39:07 -06:00    upstream-archive

9223
1

2bf91c5306 · metal : clean up · Updated 2024-01-25 05:29:45 -06:00    upstream-archive

9319
23

6ccbd1777a · wip · Updated 2024-01-24 07:45:04 -06:00    upstream-archive

9319
18

da23b56f25 · wip : no ic 8 step · Updated 2024-01-24 05:25:34 -06:00    upstream-archive

9319
18

06c2d0d117 · wip · Updated 2024-01-23 14:42:43 -06:00    upstream-archive

9319
14

a9681febd6 · ggml : online attention (CPU) · Updated 2024-01-20 08:45:41 -06:00    upstream-archive

9319
4

32a392fe68 · try a differerent fix · Updated 2024-01-19 16:10:23 -06:00    upstream-archive

9320
2

4a3bc1522e · py : linting with mypy and isort · Updated 2024-01-19 14:18:58 -06:00    upstream-archive

9321
3

1453215165 · kompute : fix ggml_add kernel · Updated 2024-01-18 16:09:16 -06:00    upstream-archive

9437
105

ccc78a200e · hellaswag: speed up even more by parallelizing log-prob evaluation · Updated 2024-01-18 10:25:29 -06:00    upstream-archive

9337
1

2917e6b528 · Merge branch 'master' into gg/imatrix-gpu-4931 · Updated 2024-01-17 10:43:45 -06:00    upstream-archive

9344
10

23742deb5b · py : fix padded dummy tokens (I hope) · Updated 2024-01-17 07:44:22 -06:00    upstream-archive

9363
4

9fd1e83f6d · Use Q4_K for attn_v for Q2_K_S when n_gqa >= 4 · Updated 2024-01-17 04:16:08 -06:00    upstream-archive

9349
1

49bafe0986 · tests : avoid creating RNGs for each tensor · Updated 2024-01-17 02:40:55 -06:00    upstream-archive

9352
6