upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-01 18:37:28 -05:00
Code Issues Packages Projects Releases Wiki Activity
11,345 Commits 829 Branches 7,706 Tags

Default Branch

master

a868c3e3c5 · hexagon: add q2_k and q3_k quant type support (#29717) · Updated 2026-10-01 16:12:25 -05:00
 ZIP  TAR.GZ

Branches

xsn/decision_clef

335afadd7a · fix merge · Updated 2026-10-01 18:24:55 -05:00
5
18
 ZIP  TAR.GZ
xsn/decision

aa07784b2e · fix py lint · Updated 2026-10-01 17:25:35 -05:00
5
15
 ZIP  TAR.GZ
gg/qwen4-fix-mask-seeds

ce5b0e0fbc · qwen4exp : optimize mask constructions · Updated 2026-10-01 15:10:42 -05:00
5
2
 ZIP  TAR.GZ
aman/fix-qwen4-asan

169ce4f27c · qwen4exp: fix tests · Updated 2026-10-01 12:54:29 -05:00
5
1
 ZIP  TAR.GZ
0cc4m/fp8-scaled-mm

07b89858e5 · add optional activation scales to mul_mat and mul_mat_id tensors · Updated 2026-10-01 11:54:07 -05:00
281
11
 ZIP  TAR.GZ
0cc4m/fp8-scaled-mm-vulkan

8968888e0e · vulkan: add fp8 and scaled matmul support · Updated 2026-10-01 11:54:07 -05:00
7
31
 ZIP  TAR.GZ
osimons/ocp_fp8_cuda

26fd61b68a · Gate mmvf_f8x2_e4m3_to_bf162 on FP8 availability, i.e. CTK >= 11.8 · Updated 2026-10-01 11:53:22 -05:00
281
7
 ZIP  TAR.GZ
osimons/ocp_fp8

574eb984df · Add supported for strided copies to/from FP8 in CPU · Updated 2026-10-01 10:59:18 -05:00
7
13
 ZIP  TAR.GZ
osimons/ocp_fp8_kv

4602e6421b · Fix get_*_scale mapping and dequnatize FP8 also before rope shift · Updated 2026-10-01 10:59:18 -05:00
7
16
 ZIP  TAR.GZ
xsn/skill0

23682f1786 · add testing instructions · Updated 2026-10-01 10:23:22 -05:00
8
2
 ZIP  TAR.GZ
allozaur/ui/model-configuration

c9b22114ab · ui : Improvements · Updated 2026-10-01 09:51:16 -05:00
9
20
 ZIP  TAR.GZ
allozaur/ui/providers-settings

d789d02899 · ui : show every provider's models in the manager · Updated 2026-10-01 09:51:16 -05:00
9
16
 ZIP  TAR.GZ
allozaur/ui/shell-polish

56460164fa · ui : polish the shell · Updated 2026-10-01 09:51:16 -05:00
9
22
 ZIP  TAR.GZ
allozaur/ui/models-discover

611a23da56 · ui : add the Enable Discover Models setting · Updated 2026-10-01 09:50:08 -05:00
9
12
 ZIP  TAR.GZ
gg/ggml-prune-deprecated

25c27513f3 · cont : fix backward · Updated 2026-10-01 09:47:16 -05:00
13
4
 ZIP  TAR.GZ
allozaur/server-download-sidecar-tags

db15a5ed96 · common : resolve <quant>-<sidecar> download tags and list cached sidecars · Updated 2026-10-01 09:42:02 -05:00
9
8
 ZIP  TAR.GZ
allozaur/ui/models-manager

34d4934dea · ui : default to the Hub metadata and hide avatars when it is off · Updated 2026-10-01 09:42:02 -05:00
9
7
 ZIP  TAR.GZ
aman/qwen4-mtp

e70959a4aa · cont : clean-up comments · Updated 2026-10-01 06:11:09 -05:00
18
7
 ZIP  TAR.GZ
aman/qwen4-opt

f2ef14ea8b · qwen4exp: keep kq_mask input the same shape · Updated 2026-10-01 05:45:03 -05:00
18
2
 ZIP  TAR.GZ
0cc4m/vulkan-pipeline-error-logging

f8e9674f28 · vulkan: add logging to pipeline compile issues · Updated 2026-10-01 04:11:28 -05:00
20
1
 ZIP  TAR.GZ