ggml-org/llama.cpp
0
0 Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-21 09:09:40 +08:00
Code Issues Packages Projects Releases Wiki Activity
11,783 Commits 878 Branches 8,073 Tags

Default Branch

master

339f3242c7 · opencl: fix rope program build error with newer Clang (#30893) · Updated 2026-10-21 08:19:08 +08:00
 ZIP  TAR.GZ

Branches

0cc4m/vulkan-ggml-prec-support

a1024c4396 · don't scale if disabled · Updated 2026-10-19 16:59:03 +08:00
29
6
 ZIP  TAR.GZ
allozaur/feat/settings-show-tool-call-in-progress

d5c3326580 · fix(ui): stream file tool bodies even before a path arrives · Updated 2026-10-19 14:26:56 +08:00
5
2
 ZIP  TAR.GZ
allozaur/ui/models-discover

68f7dd242d · common : check the saved etag before resuming a partial download · Updated 2026-10-17 04:22:03 +08:00
8
22
 ZIP  TAR.GZ
xsn/skill_slice_model

46d81a8995 · add to agents.md · Updated 2026-10-17 03:42:09 +08:00
5
3
 ZIP  TAR.GZ
0cc4m/fp8-scaled-mm-vulkan

77fc6f6cdd · vulkan: add fp8 and scaled matmul support · Updated 2026-10-17 03:08:25 +08:00
3
25
 ZIP  TAR.GZ
0cc4m/fp8-scaled-mm

a06027dcf8 · add optional activation scales to mul_mat and mul_mat_id tensors · Updated 2026-10-17 03:08:24 +08:00
74
66
 ZIP  TAR.GZ
osimons/ocp_fp8_cuda

d35a3eded6 · Explicitly link against cublaslt · Updated 2026-10-17 03:08:09 +08:00
143
30
 ZIP  TAR.GZ
osimons/ocp_fp8

5dee337b49 · Fix lint + execute tests · Updated 2026-10-17 02:55:06 +08:00
21
8
 ZIP  TAR.GZ
osimons/ocp_fp8_kv

e4cd952028 · Fix linting errors of test_kv_cache_scales · Updated 2026-10-17 02:55:06 +08:00
57
16
 ZIP  TAR.GZ
xsn/server_engine

5e59982160 · engine: separate engine and server · Updated 2026-10-17 02:17:40 +08:00
3
1
 ZIP  TAR.GZ
aman/sched-host-async

4815e5e769 · ggml: allow input async copies · Updated 2026-10-17 01:26:16 +08:00
85
1
 ZIP  TAR.GZ
gg/metal-fusion-hc-post

0df3a2db84 · metal : fuse qwen4exp's SCALE -> SIGMOID -> SCALE -> hc_post chain · Updated 2026-10-16 23:31:55 +08:00
12
1
 ZIP  TAR.GZ
0cc4m/vulkan-scratch-buffers

03980566c0 · add size safeguard · Updated 2026-10-16 17:56:00 +08:00
1
4
 ZIP  TAR.GZ
cisc/ci-amd-gfx1201-jobs

fec5711033 · add 1accel label [no ci] · Updated 2026-10-16 17:25:47 +08:00
0
0
 Included
 ZIP  TAR.GZ
aman/vecdot-opt

6e9b69aa9e · ggml-cuda: hip: small nwarps GCN fix on Q3_K(ncols=2,3), Q6_K(ncols=4) · Updated 2026-10-16 15:20:33 +08:00
4
1
 ZIP  TAR.GZ
aman/cuda-kpool-mask

8a86212329 · enroll glm5.3-next too · Updated 2026-10-16 11:36:06 +08:00
70
2
 ZIP  TAR.GZ
xsn/mtmd_audio_stream

7bc6c2b840 · address review · Updated 2026-10-16 06:00:01 +08:00
2
3
 ZIP  TAR.GZ
allozaur/fix/ui-agentic-max-turns-default

4fa59473db · fix(ui): take the agentic turns default from DEFAULT_AGENTIC_CONFIG · Updated 2026-10-15 17:34:52 +08:00
13
1
 ZIP  TAR.GZ
gg/llama-prune

13feea5fd8 · llama : remove deprecated llama_set_warmup · Updated 2026-10-15 13:28:48 +08:00
0
1
 ZIP  TAR.GZ
allozaur/ui/model-configuration

95425cca6d · ui : let the delete action scroll with the model it removes · Updated 2026-10-14 21:47:30 +08:00
8
34
 ZIP  TAR.GZ