Default Branch

d2ecd2d1cf · common/parser: add --skip-chat-parsing to force a pure content parser. (#20289) · Updated 2026-03-17 15:16:43 +00:00

Branches

3f62ee8bee · metal : back to a single queue per device · Updated 2025-09-09 14:06:46 +00:00    sdgoij

1970
9

7b717fb4b2 · Rewrite llama-run to use llama-server · Updated 2025-09-05 16:22:36 +00:00    sdgoij

2007
1

9f2636b7dc · wip · Updated 2025-09-01 08:17:56 +00:00    sdgoij

2056
1

4317d5abf5 · wip · Updated 2025-08-28 10:55:21 +00:00    sdgoij

2090
1

dc2187d48d · ggml : fix SSM_SCAN for n_groups > 1 · Updated 2025-08-27 21:37:04 +00:00    sdgoij

2095
1

fb573f4440 · ggml-quants : avoid division by zero in make_q3_quants · Updated 2025-08-17 22:26:02 +00:00    sdgoij

2210
2

220860aa0c · graph : use F32 accumulators for gpt-oss · Updated 2025-08-14 13:08:31 +00:00    sdgoij

2237
1

d9b625edb6 · ggml-quants : handle imatrix for MXFP4 · Updated 2025-08-12 02:12:10 +00:00    sdgoij

2263
1

2763dc8b53 · ggml-quants : handle zero amax for MXFP4 · Updated 2025-08-06 20:26:25 +00:00    sdgoij

2301
2

2ec70c964b · tests: Fix OPT_STEP_SGD test-backend-ops · Updated 2025-08-05 04:57:14 +00:00    sdgoij

2309
4

145401c9e3 · context : fix logits size overflow for huge batches · Updated 2025-08-05 02:26:46 +00:00    sdgoij

2308
2

342e7014db · imatrix : only warn about suffix when output format is unspecified · Updated 2025-08-04 19:12:27 +00:00    sdgoij

2313
2

e549515cb3 · memory : handle kv_unified for hybrid models · Updated 2025-08-03 04:45:47 +00:00    sdgoij

2322
1

91e67b8583 · imatrix : fix 3d tensor counts · Updated 2025-07-31 15:56:38 +00:00    sdgoij

2350
4

b98f80a6b4 · server : test alternative LRU logic · Updated 2025-07-29 18:19:21 +00:00    sdgoij

2371
1

0591b39e48 · ops: add MUSA · Updated 2025-07-29 09:25:32 +00:00    sdgoij

2377
1

381879e0ac · cont : tmp · Updated 2025-07-29 04:42:55 +00:00    sdgoij

2401
3

fb371c18ec · bench,common : add CPU extra buffer types · Updated 2025-07-28 18:53:18 +00:00    sdgoij

2378
1

e9f7e7cce2 · ops : update BLAS · Updated 2025-07-28 06:42:57 +00:00    sdgoij

2388
1

a5801f408f · sync : ggml · Updated 2025-07-25 11:31:39 +00:00    sdgoij

2407
2