jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity
9,828 Commits 609 Branches 6,686 Tags

Default Branch

master

ebd048fc5e · opencl: flash attention improvement (#25069) · Updated 2026-06-27 17:36:06 -05:00
 ZIP  TAR.GZ

Branches

gg/metal-capture-env-cont

8c8544f9fb · metal : fix capture_compute counter logic · Updated 2026-03-11 11:35:45 -05:00    jdelony

1535
1
 ZIP  TAR.GZ
0cc4m/vulkan-coopmat-int8

715ed28683 · use scalar sums · Updated 2026-03-07 15:11:40 -06:00    jdelony

1596
3
 ZIP  TAR.GZ
pr/19802-test

121fe62182 · test · Updated 2026-03-06 08:30:32 -06:00    jdelony

1612
7
 ZIP  TAR.GZ
ci-tmp

4b436e4e5e · flake8 fix · Updated 2026-02-23 04:48:01 -06:00    jdelony

1720
20
 ZIP  TAR.GZ
JohannesGaessler/ggml-meta-backend-8-tmp

5d45884106 · metal : fix build · Updated 2026-02-18 01:14:31 -06:00    jdelony

1827
23
 ZIP  TAR.GZ
pr/19378

5da56dc1d8 · args : add -kvu to llama-parallel · Updated 2026-02-12 13:50:01 -06:00    jdelony

1827
17
 ZIP  TAR.GZ
pr/19378-test-tp

e7fbfc9b80 · ci : tmp fixes · Updated 2026-02-11 07:48:40 -06:00    jdelony

1877
22
 ZIP  TAR.GZ
gg/qwen3-next-opt-tmp

5372fc6461 · wip · Updated 2026-02-10 15:44:42 -06:00    jdelony

1842
18
 ZIP  TAR.GZ
pr/17795-test-ci

b9b56b017e · Apply suggestion from @ggerganov (src->buffer to buf_src) v2 · Updated 2026-02-10 05:00:44 -06:00    jdelony

1842
13
 ZIP  TAR.GZ
gg/ci-sanitize-less-threads

5144018e7b · cont : simplify · Updated 2026-02-07 06:50:05 -06:00    jdelony

1863
4
 ZIP  TAR.GZ
gg/qwen3next-fix-chunking

1213a03564 · qwen3next : fix chunking · Updated 2026-02-04 02:06:38 -06:00    jdelony

1896
1
 ZIP  TAR.GZ
gg/compare-mlx

5b01d8575d · examples : add compare-mlx · Updated 2026-01-31 01:57:35 -06:00    jdelony

1933
1
 ZIP  TAR.GZ
gg/ngram-mod

6c8a04576e · experiments · Updated 2026-01-28 01:45:07 -06:00    jdelony

1984
29
 ZIP  TAR.GZ
gg/quant-manual-overrides

8b407e3978 · quant : manual overrides of tensor types take precedence · Updated 2026-01-20 03:20:24 -06:00    jdelony

2048
1
 ZIP  TAR.GZ
gg/winget-update

3bfbbcc5fc · winget : update komac version · Updated 2026-01-18 02:29:03 -06:00    jdelony

2058
1
 ZIP  TAR.GZ
gg/kv-mask-opt-verify

e2751545b9 · cont : inline verification · Updated 2026-01-17 06:33:07 -06:00    jdelony

2070
5
 ZIP  TAR.GZ
b7739

36f0132464 · CUDA: Factor out and re-use block_reduce function (#18785) · Updated 2026-01-14 20:44:54 -06:00    jdelony

2089
0
 Included
 ZIP  TAR.GZ
gg/fit-params-ngl

60864997fe · fit-params : print signed int for -ngl param · Updated 2026-01-14 11:59:23 -06:00    jdelony

2092
1
 ZIP  TAR.GZ
pr/18490

08b5d956fc · minor : std::unordered_set over std::set · Updated 2026-01-12 05:35:25 -06:00    jdelony

2245
3
 ZIP  TAR.GZ
gg/server-refactor

4a2751258a · server : simplify prompt state transition branches · Updated 2026-01-09 09:46:03 -06:00    jdelony

2144
11
 ZIP  TAR.GZ