ggml-org/llama.cpp
0
0 Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-22 09:39:53 +08:00
Code Issues Packages Projects Releases Wiki Activity
11,804 Commits 881 Branches 8,107 Tags

Default Branch

master

c7fc509417 · opencl: add F32-to-I32 ARGMAX (#30897) · Updated 2026-10-22 09:02:50 +08:00
 ZIP  TAR.GZ

Branches

0cc4m/vulkan-async-p2p

4cabbe36e0 · state · Updated 2026-04-09 19:00:31 +08:00    tqcq

2838
16
 ZIP  TAR.GZ
0cc4m/cpu-arm-nvfp4-fix

a30369d515 · cpu: fix ARM NEON nvfp4 vec dot · Updated 2026-04-06 16:27:03 +08:00    tqcq

2869
1
 ZIP  TAR.GZ
copilot/compare-kv-shifting-implementation

c30e012253 · contrib : rewrite AGENTS.md, make it more clear about project values (#21270) · Updated 2026-04-02 05:31:51 +08:00    tqcq

2914
0
 Included
 ZIP  TAR.GZ
gg/attn-rot-rand

f0fea264b0 · cont : rand hadamard matrices · Updated 2026-03-28 02:11:47 +08:00    tqcq

3003
4
 ZIP  TAR.GZ
gg/attn-rot-wip

ff76c6731d · cont : cache shift support · Updated 2026-03-27 20:39:14 +08:00    tqcq

3003
4
 ZIP  TAR.GZ
xsn/ai_policy_private_repo

4cd732f445 · better wording · Updated 2026-03-26 02:46:17 +08:00    tqcq

3013
2
 ZIP  TAR.GZ
pr/20394

07a6fd8775 · kleidiai: removed cpu feature detection from CI run script · Updated 2026-03-25 01:24:41 +08:00    tqcq

3253
3
 ZIP  TAR.GZ
gg/release-disable-s390x

203eec25c0 · releases : disable s390x builds · Updated 2026-03-21 01:31:25 +08:00    tqcq

3084
1
 ZIP  TAR.GZ
gg/gguf-fix-division-by-zero

4af94d9afe · gguf : fix division by zero · Updated 2026-03-18 18:39:19 +08:00    tqcq

3134
1
 ZIP  TAR.GZ
gg/ci-build-cro

15324f905b · cont : reduce paths · Updated 2026-03-15 19:03:20 +08:00    tqcq

3185
3
 ZIP  TAR.GZ
0cc4m/vulkan-async-fixes2

0776a6a039 · remove event pending stage · Updated 2026-03-15 16:00:06 +08:00    tqcq

3216
10
 ZIP  TAR.GZ
0cc4m/vulkan-slang-flash-attention

5ec6569eb5 · unify scalar+vector and fix reduce function · Updated 2026-03-13 16:23:03 +08:00    tqcq

3217
6
 ZIP  TAR.GZ
compilade/imatrix-neutral-prior

95ae9982d3 · Merge branch 'master' into compilade/imatrix-neutral-prior · Updated 2026-03-13 01:20:00 +08:00    tqcq

3219
6
 ZIP  TAR.GZ
0cc4m/vulkan-mm-pipeline-selection

7ded1269ab · unify matmul_id shader selection · Updated 2026-03-12 21:55:12 +08:00    tqcq

3220
2
 ZIP  TAR.GZ
gg/metal-bin-mod

20fbf04cd6 · metal : fix capture_started flag · Updated 2026-03-12 05:15:16 +08:00    tqcq

3242
2
 ZIP  TAR.GZ
gg/metal-capture-env-cont

8c8544f9fb · metal : fix capture_compute counter logic · Updated 2026-03-12 00:35:45 +08:00    tqcq

3248
1
 ZIP  TAR.GZ
pr/19802-test

121fe62182 · test · Updated 2026-03-06 22:30:32 +08:00    tqcq

3325
7
 ZIP  TAR.GZ
ci-tmp

4b436e4e5e · flake8 fix · Updated 2026-02-23 18:48:01 +08:00    tqcq

3433
20
 ZIP  TAR.GZ
JohannesGaessler/ggml-meta-backend-8-tmp

5d45884106 · metal : fix build · Updated 2026-02-18 15:14:31 +08:00    tqcq

3540
23
 ZIP  TAR.GZ
pr/19378

5da56dc1d8 · args : add -kvu to llama-parallel · Updated 2026-02-13 03:50:01 +08:00    tqcq

3540
17
 ZIP  TAR.GZ