Default Branch

84e908c625 · ci: fix thread sanitizer + remove ccache (#26927) · Updated 2026-08-12 20:01:12 +04:00

Branches

56fe6a8187 · models : fix dflash wo_a reshape on load · Updated 2026-08-04 17:41:42 +04:00

129
1

201e50cc20 · clean up comments · Updated 2026-08-04 17:18:19 +04:00

145
56

eb75c420f0 · Shared default of 64 for history-based samplers, remove context_size · Updated 2026-08-04 10:02:53 +04:00

139
2

3dfb7c7fad · server: simplify get_info result handling · Updated 2026-08-03 20:22:56 +04:00

150
4

7f5903206c · correct to 9931 · Updated 2026-08-03 14:18:50 +04:00

158
3

9d74f019e6 · ggml-meta: make sure to call init_tensor for all new tensors · Updated 2026-08-03 10:22:59 +04:00

161
2

ddd9cdb158 · reuse str_to_lower from server-models · Updated 2026-08-02 22:41:31 +04:00

174
2

1e95e764b1 · fix convert bug · Updated 2026-08-02 18:35:46 +04:00

169
3

a850ca8c62 · test: fix some CI errors · Updated 2026-08-02 01:15:10 +04:00

177
1

37e22b750e · improve Security review a bit · Updated 2026-08-01 19:48:31 +04:00

179
2

55467b6b66 · fix build · Updated 2026-07-31 12:08:09 +04:00

208
23

10329a2abc · mtmd: add n_embd_head · Updated 2026-07-31 00:14:00 +04:00

197
1

f531c878c2 · mtmd: add lanczos resize method · Updated 2026-07-30 23:23:15 +04:00

200
1

76bb9cb0ad · fix ~server_batch() · Updated 2026-07-30 20:31:20 +04:00

208
2

a0f1a44b8d · rm has_logit_bias · Updated 2026-07-29 18:41:54 +04:00

216
3

96ece714c4 · metal : per-device tuned (Q, NE) for flash-attn vec (#25750) · Updated 2026-07-29 17:46:01 +04:00

227
8

72d0d8de4e · common_http_client · Updated 2026-07-29 01:51:35 +04:00

224
1

001600ceb9 · fix types · Updated 2026-07-28 17:09:28 +04:00

232
14

f45ca59f0f · server: abstract llama_memory calls to common_memory · Updated 2026-07-28 13:36:16 +04:00

236
1

be4c137590 · nits 2 · Updated 2026-07-27 23:35:03 +04:00

248
5