Default Branch

fe2adf0e72 · vendor : update BoringSSL to 0.20260803.0 (#26523) · Updated 2026-08-03 13:31:15 -05:00

Branches

e83ef74733 · one less magic number · Updated 2025-09-20 00:58:36 -05:00    upstream-archive

3744
6

652d303b32 · metal : fuse add + rms · Updated 2025-09-18 08:29:25 -05:00    upstream-archive

3742
1

64c6dcbe6d · metal : make the NSG a function constant in mul_mv kernels · Updated 2025-09-18 03:31:59 -05:00    upstream-archive

3747
2

6045c5a263 · cont : put all buffers in the same virtual address space · Updated 2025-09-14 07:46:57 -05:00    upstream-archive

3783
2

3f62ee8bee · metal : back to a single queue per device · Updated 2025-09-09 09:06:46 -05:00    upstream-archive

3825
9

3f62ee8bee · metal : back to a single queue per device · Updated 2025-09-09 09:06:46 -05:00    upstream-archive

3825
9

7b717fb4b2 · Rewrite llama-run to use llama-server · Updated 2025-09-05 11:22:36 -05:00    upstream-archive

3862
1

9f2636b7dc · wip · Updated 2025-09-01 03:17:56 -05:00    upstream-archive

3911
1

4317d5abf5 · wip · Updated 2025-08-28 05:55:21 -05:00    upstream-archive

3945
1

dc2187d48d · ggml : fix SSM_SCAN for n_groups > 1 · Updated 2025-08-27 16:37:04 -05:00    upstream-archive

3950
1

fb573f4440 · ggml-quants : avoid division by zero in make_q3_quants · Updated 2025-08-17 17:26:02 -05:00    upstream-archive

4065
2

220860aa0c · graph : use F32 accumulators for gpt-oss · Updated 2025-08-14 08:08:31 -05:00    upstream-archive

4092
1

d9b625edb6 · ggml-quants : handle imatrix for MXFP4 · Updated 2025-08-11 21:12:10 -05:00    upstream-archive

4118
1

2763dc8b53 · ggml-quants : handle zero amax for MXFP4 · Updated 2025-08-06 15:26:25 -05:00    upstream-archive

4156
2

2ec70c964b · tests: Fix OPT_STEP_SGD test-backend-ops · Updated 2025-08-04 23:57:14 -05:00    upstream-archive

4164
4

145401c9e3 · context : fix logits size overflow for huge batches · Updated 2025-08-04 21:26:46 -05:00    upstream-archive

4163
2

342e7014db · imatrix : only warn about suffix when output format is unspecified · Updated 2025-08-04 14:12:27 -05:00    upstream-archive

4168
2

e549515cb3 · memory : handle kv_unified for hybrid models · Updated 2025-08-02 23:45:47 -05:00    upstream-archive

4177
1

91e67b8583 · imatrix : fix 3d tensor counts · Updated 2025-07-31 10:56:38 -05:00    upstream-archive

4205
4

b98f80a6b4 · server : test alternative LRU logic · Updated 2025-07-29 13:19:21 -05:00    upstream-archive

4226
1