1
mirror of https://github.com/ggerganov/llama.cpp synced 2025-10-03 09:21:03 +02:00

Default Branch

136bda78c5 · webui : Fix messages payload sent to chat completions (#16402) · Updated 2025-10-03 09:11:34 +02:00

Branches

b98f80a6b4 · server : test alternative LRU logic · Updated 2025-07-29 20:19:21 +02:00

649
1

0591b39e48 · ops: add MUSA · Updated 2025-07-29 11:25:32 +02:00

655
1

381879e0ac · cont : tmp · Updated 2025-07-29 06:42:55 +02:00

679
3

fb371c18ec · bench,common : add CPU extra buffer types · Updated 2025-07-28 20:53:18 +02:00

656
1

e9f7e7cce2 · ops : update BLAS · Updated 2025-07-28 08:42:57 +02:00

666
1

a5801f408f · sync : ggml · Updated 2025-07-25 13:31:39 +02:00

685
2

6f4c57236b · server : fix vision test regex · Updated 2025-07-25 10:22:36 +02:00

707
1

aa5a7c6d6d · profiler: output all tensor names · Updated 2025-07-25 04:14:41 +02:00

690
2

e65aa69402 · context : only sort outputs when needed · Updated 2025-07-24 17:06:34 +02:00

694
1

a124399f19 · sched : fix multiple evaluations of the same graph with pipeline parallelism · Updated 2025-07-24 16:03:14 +02:00

694
1

978c88ba0a · cont : add TODO · Updated 2025-07-24 15:31:10 +02:00

696
2

1ef3cc1a87 · imatrix : use GGUF regardless of the output filename · Updated 2025-07-24 05:22:41 +02:00

701
2

55cf48de1e · cuda : fix multi-seq, quantized FA · Updated 2025-07-22 19:48:53 +02:00

743
2

0a0af0dbbd · Vulkan: Fix fprintf format-security warning · Updated 2025-07-19 11:45:31 +02:00

737
1

386892ec61 · sync : ggml · Updated 2025-07-19 10:46:12 +02:00

738
1

cfe5e98423 · graph : fix graph reuse reset of params · Updated 2025-07-18 16:50:32 +02:00

741
1

9106d7595d · model : fix build after merge conflict · Updated 2025-07-18 10:50:59 +02:00

744
1

05baa62a73 · kv-cache : fix k-shift for multiple streams · Updated 2025-07-17 19:18:36 +02:00

753
1

07908a824a · server : pre-calculate EOG logit biases · Updated 2025-07-16 12:47:05 +02:00

766
1

9f8d285901 · server : fix handling of the ignore_eos flag · Updated 2025-07-16 06:37:18 +02:00

771
1