Default Branch

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

Branches

dc2187d48d · ggml : fix SSM_SCAN for n_groups > 1 · Updated 2025-08-28 05:37:04 +08:00    tqcq

5213
1

fb573f4440 · ggml-quants : avoid division by zero in make_q3_quants · Updated 2025-08-18 06:26:02 +08:00    tqcq

5328
2

220860aa0c · graph : use F32 accumulators for gpt-oss · Updated 2025-08-14 21:08:31 +08:00    tqcq

5355
1

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

5381
1

2763dc8b53 · ggml-quants : handle zero amax for MXFP4 · Updated 2025-08-07 04:26:25 +08:00    tqcq

5419
2

2ec70c964b · tests: Fix OPT_STEP_SGD test-backend-ops · Updated 2025-08-05 12:57:14 +08:00    tqcq

5427
4

145401c9e3 · context : fix logits size overflow for huge batches · Updated 2025-08-05 10:26:46 +08:00    tqcq

5426
2

342e7014db · imatrix : only warn about suffix when output format is unspecified · Updated 2025-08-05 03:12:27 +08:00    tqcq

5431
2

e549515cb3 · memory : handle kv_unified for hybrid models · Updated 2025-08-03 12:45:47 +08:00    tqcq

5440
1

91e67b8583 · imatrix : fix 3d tensor counts · Updated 2025-07-31 23:56:38 +08:00    tqcq

5153
4

b98f80a6b4 · server : test alternative LRU logic · Updated 2025-07-30 02:19:21 +08:00    tqcq

5174
1

0591b39e48 · ops: add MUSA · Updated 2025-07-29 17:25:32 +08:00    tqcq

5180
1

381879e0ac · cont : tmp · Updated 2025-07-29 12:42:55 +08:00    tqcq

5204
3

fb371c18ec · bench,common : add CPU extra buffer types · Updated 2025-07-29 02:53:18 +08:00    tqcq

5181
1

e9f7e7cce2 · ops : update BLAS · Updated 2025-07-28 14:42:57 +08:00    tqcq

5191
1

a5801f408f · sync : ggml · Updated 2025-07-25 19:31:39 +08:00    tqcq

5210
2

6f4c57236b · server : fix vision test regex · Updated 2025-07-25 16:22:36 +08:00    tqcq

5232
1

e65aa69402 · context : only sort outputs when needed · Updated 2025-07-24 23:06:34 +08:00    tqcq

5219
1

a124399f19 · sched : fix multiple evaluations of the same graph with pipeline parallelism · Updated 2025-07-24 22:03:14 +08:00    tqcq

5219
1

978c88ba0a · cont : add TODO · Updated 2025-07-24 21:31:10 +08:00    tqcq

5221
2