happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
7,444 Commits 517 Branches 5,070 Tags 998 MiB

Default Branch

master

58062860af · ggml : use WARP_SIZE/2 for argmax reduction offset (#18092) · Updated 2025-12-16 19:47:01 -08:00
 ZIP  TAR.GZ

Branches

sl/realloc-error-cont

6cdda87baf · ci : disable op offload in some tests · Updated 2025-11-20 07:16:50 -08:00
357
3
 ZIP  TAR.GZ
graph-profiler

c58a3bf677 · prof: fix tensor dims formatter · Updated 2025-11-18 17:58:15 -08:00
362
3
 ZIP  TAR.GZ
revert-17192-test

4a83611773 · Revert "CANN: Add openEuler-cann in build and release (#17192)" · Updated 2025-11-18 01:00:05 -08:00
350
1
 ZIP  TAR.GZ
0cc4m/vulkan-mmq-bk-step-tuning

dba1cbceb3 · tune for RDNA3 · Updated 2025-11-16 11:21:22 -08:00
365
4
 ZIP  TAR.GZ
gg/metal-set-rows-threads

e6dbc81569 · metal : cap threadgroups size of set_rows · Updated 2025-11-10 06:17:09 -08:00
434
1
 ZIP  TAR.GZ
gg/fa-no-kq-pad

3ad533689c · ggml : remove KQ mask padding · Updated 2025-11-10 04:35:25 -08:00
436
1
 ZIP  TAR.GZ
compilade/convert-reflinks

2ef41855cf · convert : for FP8, use scale type to decide auto type · Updated 2025-11-06 19:55:53 -08:00
474
16
 ZIP  TAR.GZ
compilade/convert-safetensors-parse

e996f3aef8 · convert : fix no-lazy dtypes from direct safetensors · Updated 2025-11-06 19:33:09 -08:00
474
3
 ZIP  TAR.GZ
compilade/convert-prequant-compressed-tensors

128118fdbe · convert : use F32 for dequant of pack-quantized tensors · Updated 2025-11-06 18:59:32 -08:00
474
6
 ZIP  TAR.GZ
copilot/test-branch

23b70f4f70 · Initial plan · Updated 2025-11-04 03:00:12 -08:00
502
1
 ZIP  TAR.GZ
xsn/mtmd_custom_min_max_tokens

79b98dbf96 · Merge branch 'master' into xsn/mtmd_custom_min_max_tokens · Updated 2025-11-02 13:14:03 -08:00
517
2
 ZIP  TAR.GZ
gg/clip-fa

d441c31b19 · metal : remove stray return · Updated 2025-11-02 08:24:00 -08:00
526
9
 ZIP  TAR.GZ
compilade/fix-prequant-mxfp4-gpt-oss

d7f794eadb · convert : avoid dequantizing mxfp4 for GPT-OSS · Updated 2025-10-24 04:56:26 -07:00
613
1
 ZIP  TAR.GZ
compilade/convert-prequant

93fbd407f3 · Merge branch 'master' into compilade/convert-prequant · Updated 2025-10-23 11:23:12 -07:00
616
6
 ZIP  TAR.GZ
gg/metal-alloc-size

f0076dc5a0 · metal : adjust .get_alloc_size to be alloc friendly · Updated 2025-10-19 07:20:54 -07:00
646
1
 ZIP  TAR.GZ
gg/fix-amx

96f9f391c7 · ggml : fix unaligned access in AMX code · Updated 2025-09-29 00:37:15 -07:00
826
1
 ZIP  TAR.GZ
gg/fix-sve

a8b0089a5b · ggml : remove SVE paths · Updated 2025-09-28 10:26:03 -07:00
826
1
 ZIP  TAR.GZ
gg/fa-no-kq-pad-save

837b1b4563 · ggml : remove KQ mask padding · Updated 2025-09-28 08:10:17 -07:00
829
6
 ZIP  TAR.GZ
llama-pull

17ca6ed540 · Implement llama-pull tool · Updated 2025-09-20 09:25:21 -07:00
917
1
 ZIP  TAR.GZ
xsn/qwen3next_experiment

e83ef74733 · one less magic number · Updated 2025-09-19 22:58:36 -07:00
936
6
 ZIP  TAR.GZ