Default Branch

bc091a4dc5 · common : Define cache directory on AIX (#12915) · Updated 2025-04-12 15:33:39 +00:00

Branches

a6f3aca617 · restore local workgroup size adjustments for large inputs · Updated 2025-04-12 06:08:06 +00:00

2
2

3fe362fe49 · gguf-py : use ThreadPoolExecutor when writing tensors · Updated 2025-04-12 04:00:51 +00:00

39
2

fd058988e1 · SYCL: Add ROPE vision kernel · Updated 2025-04-12 03:11:19 +00:00

15
1

51e6e0079c · threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling · Updated 2025-04-11 20:20:06 +00:00

4
1

9ebaab6bff · cont : use MTLHeapTypePlacement · Updated 2025-04-11 10:55:19 +00:00

8
11

625a7a7853 · ggml : add x64 base ABI variant · Updated 2025-04-10 18:31:24 +00:00

24
2

098f0e5eea · test · Updated 2025-04-10 09:35:16 +00:00

24
1

e9e1882d2d · rm tail space · Updated 2025-04-08 05:43:11 +00:00

47
4

da140da72a · gguf-py : fix flake8 lint · Updated 2025-04-07 23:38:35 +00:00

47
2

19eb81e083 · kv-cache : serparate recurrent vs non-recurrent impl (wip) · Updated 2025-04-07 13:55:46 +00:00

60
1

ced26486ff · cont · Updated 2025-04-07 12:24:01 +00:00

59
6

ab27292b26 · Use dot instruction to multiply two values at once, to enable dual issue instructions · Updated 2025-04-06 10:32:35 +00:00

61
2

fe564b0dfb · ci : rename job MSVC -> MinGW · Updated 2025-04-04 10:51:48 +00:00

74
1

43ab09b85d · ci : testing (wip) · Updated 2025-04-04 10:43:43 +00:00

74
1

7a73e861a7 · cont · Updated 2025-04-04 09:02:20 +00:00

83
4

c875e03f96 · rpc : update README for cache usage · Updated 2025-03-28 07:41:47 +00:00

140
1

efe0222130 · media : add SVG logo [no ci] · Updated 2025-03-27 21:07:46 +00:00

143
1

70b063a550 · metal : reduce register pressure · Updated 2025-03-26 19:24:28 +00:00

171
8

20b256e0fd · convert : match ssm_conv tensors by type · Updated 2025-03-25 18:29:22 +00:00

164
2

e94c2bd360 · ggml : improve repack templates · Updated 2025-03-25 07:42:31 +00:00

176
2