Default Branch

4ebdf2c74a · ci : use t4-medium for cuda jobs (#29842) · Updated 2026-10-02 10:31:19 -05:00

Branches

b7d9c4ccaf · nits · Updated 2026-08-12 10:19:57 -05:00

992
20

f370471abf · adapt to upstream changes · Updated 2026-08-11 07:00:58 -05:00

1002
2

f236e272f0 · rm gen_flow_temp · Updated 2026-08-10 18:01:16 -05:00

1014
18

35d6100372 · ci: add pr-draft-label · Updated 2026-08-09 06:50:12 -05:00

1036
1

d483b9b3aa · x-tool-docker --> x-tool-runtime · Updated 2026-08-07 18:48:51 -05:00

1043
11

ae86645c28 · Consistify polling frequency of llama-bench with args · Updated 2026-08-07 13:59:38 -05:00

1044
1

b8b8738f92 · Merge branch 'master' into xsn/fix_longest_edge_with_limit · Updated 2026-08-07 08:38:55 -05:00

1079
3

fbb29b3f98 · address review comments · Updated 2026-08-07 07:40:02 -05:00

1057
5

1621aade61 · server: (router) do not evict busy models · Updated 2026-08-07 07:38:06 -05:00

1058
1

1a0e158115 · fix it · Updated 2026-08-06 06:30:01 -05:00

1079
2

6751477adf · cont : avoid copy_state · Updated 2026-08-06 02:19:52 -05:00

1081
14

f8fa4df82a · test: add duplicated index case for ggml_mul_mat_id · Updated 2026-08-05 18:16:17 -05:00

1079
1

f7655b451d · server: fix empty response for /cors-proxy · Updated 2026-08-05 18:09:24 -05:00

1079
1

91f82eb1b4 · mtmd: fix granite 4v grid assembly · Updated 2026-08-05 17:42:06 -05:00

1080
1

0377fc17ad · sampler : add llama_sampler_copy · Updated 2026-08-05 06:40:53 -05:00

1093
2

e77293d4cc · mtmd: weave deepseek-ocr rows in one shot instead of per row (#26615) · Updated 2026-08-05 06:07:53 -05:00

1229
2

8045779cff · cleanup · Updated 2026-08-05 03:22:33 -05:00

1092
19

ac6c66699d · vendor : apply patches for subprocess.h · Updated 2026-08-04 18:34:32 -05:00

1093
1

58137f0f47 · quant : allow quantization of ffn_gate_inp tensors · Updated 2026-08-04 10:11:42 -05:00

1101
1

285941de20 · nits 2 · Updated 2026-08-04 09:49:43 -05:00

1100
3