Default Branch

ee4c505a4f · server: add dedup-cache-models preset option (#27346) · Updated 2026-08-19 17:04:26 +08:00

Branches

ddd9cdb158 · reuse str_to_lower from server-models · Updated 2026-08-03 02:41:31 +08:00

274
2

1e95e764b1 · fix convert bug · Updated 2026-08-02 22:35:46 +08:00

269
3

a850ca8c62 · test: fix some CI errors · Updated 2026-08-02 05:15:10 +08:00

277
1

37e22b750e · improve Security review a bit · Updated 2026-08-01 23:48:31 +08:00

279
2

55467b6b66 · fix build · Updated 2026-07-31 16:08:09 +08:00

308
23

10329a2abc · mtmd: add n_embd_head · Updated 2026-07-31 04:14:00 +08:00

297
1

f531c878c2 · mtmd: add lanczos resize method · Updated 2026-07-31 03:23:15 +08:00

300
1

76bb9cb0ad · fix ~server_batch() · Updated 2026-07-31 00:31:20 +08:00

308
2

a0f1a44b8d · rm has_logit_bias · Updated 2026-07-29 22:41:54 +08:00

316
3

96ece714c4 · metal : per-device tuned (Q, NE) for flash-attn vec (#25750) · Updated 2026-07-29 21:46:01 +08:00

327
8

72d0d8de4e · common_http_client · Updated 2026-07-29 05:51:35 +08:00

324
1

f45ca59f0f · server: abstract llama_memory calls to common_memory · Updated 2026-07-28 17:36:16 +08:00

336
1

be4c137590 · nits 2 · Updated 2026-07-28 03:35:03 +08:00

348
5

7ecdaafc35 · add example · Updated 2026-07-27 17:45:54 +08:00

351
2

987e91cae2 · fix lint · Updated 2026-07-27 07:06:31 +08:00

357
2

3c5a50cc50 · mtmd: fix android build · Updated 2026-07-27 06:18:15 +08:00

357
1

474aef9770 · migrate server-mcp · Updated 2026-07-26 07:11:28 +08:00

367
9

d8efdcbdb8 · server: add format arg to datetime tool · Updated 2026-07-26 00:23:28 +08:00

373
1

33f3ec1b67 · server: make MCP test fixtures JSON-RPC 2.0 compliant · Updated 2026-07-25 23:40:53 +08:00

381
14

e7613f322d · Merge branch 'fix-rocm' into cross-profiler · Updated 2026-07-24 17:23:03 +08:00

388
17