upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-03 11:27:25 -05:00
Code Issues Packages Projects Releases Wiki Activity
11,379 Commits 831 Branches 7,739 Tags

Default Branch

master

1537a0a8b2 · server : fix laya abort by limiting n_batch to n_ubatch (#29903) · Updated 2026-10-03 10:19:13 -05:00
 ZIP  TAR.GZ

Branches

compilade/cuda-falcon-h1

1180752835 · cuda : support Falcon-H1 state size for SSM_SCAN · Updated 2025-07-09 11:18:37 -05:00    upstream-archive

5491
1
 ZIP  TAR.GZ
compilade/refactor-kv-cache

4d6a179c68 · gguf-py : avoid adding duplicate tensor mappings for Jamba · Updated 2025-07-09 10:58:35 -05:00    upstream-archive

5491
61
 ZIP  TAR.GZ
xsn/ggml_scale_bias

b7c6ece5b5 · ggml-ci · Updated 2025-07-09 07:13:34 -05:00    upstream-archive

5530
24
 ZIP  TAR.GZ
compilade/test-model-random

7634d14d7a · test-model-random : fix seq_id buffer overflow · Updated 2025-07-08 17:23:58 -05:00    upstream-archive

5530
18
 ZIP  TAR.GZ
compilade/fix-recurrent-batch-init

2ff3354c33 · memory : fix broken batch splits for recurrent cache · Updated 2025-07-07 20:23:14 -05:00    upstream-archive

5541
1
 ZIP  TAR.GZ
vb/add-smollm3

996195299e · up. · Updated 2025-07-07 16:42:40 -05:00    upstream-archive

5693
6
 ZIP  TAR.GZ
gg/metal-reuse-graphs

bf8b39015f · metal : reuse graphs · Updated 2025-07-07 13:37:07 -05:00    upstream-archive

5549
3
 ZIP  TAR.GZ
gg/kv-cache-prepare-separation

886da0a2c5 · kv-cache : prepare K/V buffers for separation · Updated 2025-07-04 02:13:16 -05:00    upstream-archive

5560
1
 ZIP  TAR.GZ
gg/llama-high-throughput-rebase

dfceb012ee · llama : add "virtual sequences" · Updated 2025-07-02 12:26:55 -05:00    upstream-archive

5571
8
 ZIP  TAR.GZ
compilade/mamba2

71bef66591 · cuda : graceful fallback for Mamba-1 models with weird embd size · Updated 2025-07-02 02:49:36 -05:00    upstream-archive

5580
44
 ZIP  TAR.GZ
gg/llama-high-throughput-save2

6179578988 · batch : require non-coupled batch with sequential split_equal · Updated 2025-06-25 09:20:46 -05:00    upstream-archive

5637
29
 ZIP  TAR.GZ
gg/llama-high-throughput-save

37bdfbef8c · wip 3 · Updated 2025-06-24 03:04:18 -05:00    upstream-archive

5637
21
 ZIP  TAR.GZ
gg/metal-fix-thread-safety

ae96333923 · metal : fix thread-safety · Updated 2025-06-20 08:42:54 -05:00    upstream-archive

5663
1
 ZIP  TAR.GZ
gg/repack-fix-wsize

6fb2f2e8a9 · ggml : fix repack work size for mul_mat_id · Updated 2025-06-20 02:34:16 -05:00    upstream-archive

5666
1
 ZIP  TAR.GZ
gabe-l-hart/HybridRecurrentCache

59fee24c72 · recurrent : rework graph inputs + add TODOs · Updated 2025-06-18 01:29:51 -05:00    upstream-archive

5690
31
 ZIP  TAR.GZ
add-pidfile

d3d06debe3 · server : add pidfile option · Updated 2025-06-17 15:47:53 -05:00    upstream-archive

5691
1
 ZIP  TAR.GZ
gg/server-reenable-swa-spec

36fce98281 · server : re-enable swa speculative decoding · Updated 2025-06-12 03:51:15 -05:00    upstream-archive

5734
1
 ZIP  TAR.GZ
gg/batch-simplify-output

ed99a8ea04 · cont : fix comments · Updated 2025-06-12 02:43:55 -05:00    upstream-archive

5737
3
 ZIP  TAR.GZ
compilade/fix-batch-reserve-rwkv

4b6fb6524b · context : round n_tokens to next multiple of n_seqs when reserving · Updated 2025-06-11 15:19:17 -05:00    upstream-archive

5740
1
 ZIP  TAR.GZ
compilade/readonly-recurrent-inputs

62a9f34bae · llama-graph : fix recurrent state copy · Updated 2025-06-09 23:26:30 -05:00    upstream-archive

5764
3
 ZIP  TAR.GZ