Default Branch

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

Branches

84f13f901c · vendor: update subprocess.h · Updated 2026-07-24 13:22:25 +08:00

389
1

c867e1c38c · llama: various bug fixes · Updated 2026-07-24 03:03:06 +08:00

390
1

b60794b60f · nits · Updated 2026-07-24 00:51:19 +08:00

392
12

ef6de50a47 · ggml: fix backend split scheduler race condition · Updated 2026-07-23 20:15:38 +08:00

393
2

4a94f386b9 · contrib: allow all AI-generated code in general · Updated 2026-07-23 01:35:20 +08:00

1
1

234252e03d · label virtual devices in description; add GPUx2 server CI jobs · Updated 2026-07-14 21:45:17 +08:00    tqcq

570
3

6554db6ed0 · add link to PR · Updated 2026-07-14 19:07:03 +08:00    tqcq

501
5

1f66d544cb · Merge branch 'master' into xsn/mtmd_ds_ocr_tiles · Updated 2026-07-10 21:11:44 +08:00    tqcq

535
13

7ab9323d1d · cli: add --output option · Updated 2026-07-09 19:44:21 +08:00    tqcq

557
1

99b9a6c08a · also show model aliases · Updated 2026-07-08 06:35:05 +08:00    tqcq

584
17

14f254515f · spec : fix naming, spacing · Updated 2026-07-07 23:52:11 +08:00    tqcq

586
1

d4a193e269 · metal : add set_rows with src0 f16 · Updated 2026-07-07 19:18:12 +08:00    tqcq

617
5

124d3d9428 · ggml: asynchronous scheduler memory copies · Updated 2026-07-05 18:47:02 +08:00    tqcq

630
1

ff9e7673cf · musaDeviceReset · Updated 2026-07-04 00:57:48 +08:00    tqcq

631
6

697372dddb · wip · Updated 2026-07-03 23:15:50 +08:00    tqcq

634
4

2d9cf41192 · check once · Updated 2026-06-29 22:03:26 +08:00    tqcq

659
12

fcf66c1d80 · correct help message · Updated 2026-06-29 01:52:36 +08:00    tqcq

665
2

0aac18be29 · use memcpy for small copies across host-visible memory · Updated 2026-06-27 18:59:58 +08:00    tqcq

671
9

c35f33b0a1 · fix missing mparams.hf_file · Updated 2026-06-26 19:17:04 +08:00    tqcq

686
2

5004859421 · server-stream : pimpl · Updated 2026-06-26 16:36:15 +08:00    tqcq

688
1