Default Branch

2da6686176 · Fix stale tensor-split params for draft models (#24814) · Updated 2026-07-05 18:39:36 +00:00

Branches

b98f80a6b4 · server : test alternative LRU logic · Updated 2025-07-29 18:19:21 +00:00    kanshan

3824
1

0591b39e48 · ops: add MUSA · Updated 2025-07-29 09:25:32 +00:00    kanshan

3830
1

381879e0ac · cont : tmp · Updated 2025-07-29 04:42:55 +00:00    kanshan

3854
3

fb371c18ec · bench,common : add CPU extra buffer types · Updated 2025-07-28 18:53:18 +00:00    kanshan

3831
1

e9f7e7cce2 · ops : update BLAS · Updated 2025-07-28 06:42:57 +00:00    kanshan

3841
1

a5801f408f · sync : ggml · Updated 2025-07-25 11:31:39 +00:00    kanshan

3888
2

6f4c57236b · server : fix vision test regex · Updated 2025-07-25 08:22:36 +00:00    kanshan

3910
1

e65aa69402 · context : only sort outputs when needed · Updated 2025-07-24 15:06:34 +00:00    kanshan

3897
1

a124399f19 · sched : fix multiple evaluations of the same graph with pipeline parallelism · Updated 2025-07-24 14:03:14 +00:00    kanshan

3897
1

978c88ba0a · cont : add TODO · Updated 2025-07-24 13:31:10 +00:00    kanshan

3899
2

1ef3cc1a87 · imatrix : use GGUF regardless of the output filename · Updated 2025-07-24 03:22:41 +00:00    kanshan

3904
2

55cf48de1e · cuda : fix multi-seq, quantized FA · Updated 2025-07-22 17:48:53 +00:00    kanshan

3946
2

386892ec61 · sync : ggml · Updated 2025-07-19 08:46:12 +00:00    kanshan

3941
1

cfe5e98423 · graph : fix graph reuse reset of params · Updated 2025-07-18 14:50:32 +00:00    kanshan

3944
1

9106d7595d · model : fix build after merge conflict · Updated 2025-07-18 08:50:59 +00:00    kanshan

3947
1

05baa62a73 · kv-cache : fix k-shift for multiple streams · Updated 2025-07-17 17:18:36 +00:00    kanshan

3956
1

07908a824a · server : pre-calculate EOG logit biases · Updated 2025-07-16 10:47:05 +00:00    kanshan

3969
1

9f8d285901 · server : fix handling of the ignore_eos flag · Updated 2025-07-16 04:37:18 +00:00    kanshan

3974
1

f68669d50f · fix and opt kernel launch · Updated 2025-07-15 11:28:26 +00:00    kanshan

4009
3

942c55cd57 · imatrix : avoid using imatrix.dat in README · Updated 2025-07-12 20:50:10 +00:00    kanshan

3994
32