ggml-org/llama.cpp
0
0 Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-21 00:59:38 +08:00
Code Issues Packages Projects Releases Wiki Activity
11,774 Commits 876 Branches 8,062 Tags

Default Branch

master

4a45de4f2c · mtmd : lfm2 tiles and layout match transformers (#30261) · Updated 2026-10-21 00:54:46 +08:00
 ZIP  TAR.GZ

Branches

aman/cpu-set-rows-wsize

34eca2264a · move set_rows to n_task = n_threads group · Updated 2026-10-13 23:43:53 +08:00
10
2
 ZIP  TAR.GZ
gg/tests-consolidate

aaa5a566a0 · cont : fix the fix · Updated 2026-10-13 19:28:02 +08:00
4
3
 ZIP  TAR.GZ
0cc4m/vulkan-tp-allreduce-opt

2a30a96d30 · code improvements · Updated 2026-10-13 03:13:40 +08:00
471
11
 ZIP  TAR.GZ
xsn/vllm_d2_q35

ad778127dd · nits · Updated 2026-10-12 21:55:36 +08:00
4
2
 ZIP  TAR.GZ
xsn/vllm_d3

fde44572a0 · Merge branch 'master' into xsn/vllm_d3 · Updated 2026-10-12 19:44:39 +08:00
1
8
 ZIP  TAR.GZ
xsn/vllm_d2

db7762d20d · rm redundant filter_tensors · Updated 2026-10-12 19:17:12 +08:00
14
8
 ZIP  TAR.GZ
gg/tests-consolidate_temp

65b4dc5b46 · tests : consolidate the context state tests into test-llama-context · Updated 2026-10-12 17:13:06 +08:00
1
10
 ZIP  TAR.GZ
0cc4m/server-memory-limit

08d69b95a2 · wip · Updated 2026-10-12 05:28:52 +08:00
978
2
 ZIP  TAR.GZ
xsn/json_patch

f0440d9efc · vendor: apply deep nested json patch from upstream · Updated 2026-10-10 05:35:12 +08:00
3
1
 ZIP  TAR.GZ
pr/29600-gg

1460533e0e · cont : clean-up · Updated 2026-10-10 03:00:47 +08:00
0
5
 ZIP  TAR.GZ
allozaur/ui/models-manager-followup

187491347b · fix: Post-review fixes · Updated 2026-10-09 23:06:03 +08:00
2
6
 ZIP  TAR.GZ
ServeurpersoCom/backend-sampling-static-graph

3fd76a33b1 · llama: keep the backend sampling graph static across ubatches · Updated 2026-10-09 18:10:08 +08:00
17
1
 ZIP  TAR.GZ
allozaur/ui/models-manager

5e4f00ab9f · refactor: Post-review fixes · Updated 2026-10-09 16:02:24 +08:00
8
18
 ZIP  TAR.GZ
0cc4m/vulkan-gdn-cm2

bfc0405353 · add tests · Updated 2026-10-09 14:22:00 +08:00
14
15
 ZIP  TAR.GZ
aman/fa-mma-q-dequant

b9e92c439e · CUDA: dequant quantized kv on-the-fly for vec kernels · Updated 2026-10-09 13:19:38 +08:00
20
1
 ZIP  TAR.GZ
xsn/port_9931

44d55b2cfc · revert unrelated changes · Updated 2026-10-09 07:14:03 +08:00
6
1
 ZIP  TAR.GZ
aman/moe-cache-multigpu

5b6850328e · use tensor split for deciding cache size · Updated 2026-10-08 17:57:29 +08:00
0
1
 ZIP  TAR.GZ
maxk/hexagon-alloc-buffer-n

16f9f9a0c0 · Update scripts/snapdragon/run.py · Updated 2026-10-08 09:23:40 +08:00
85
10
 ZIP  TAR.GZ
xsn/embd_gemma2

1e91a0b054 · model: support embeddinggemma2 (text+vision+audio) · Updated 2026-10-06 23:59:06 +08:00
5
1
 ZIP  TAR.GZ
rpc_tensor

bfa00faa98 · rpc: bump major version · Updated 2026-10-06 23:06:47 +08:00
114
3
 ZIP  TAR.GZ