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

xsn/server_sleep_proc

e12b6c2c04 · nits · Updated 2026-08-20 07:31:47 +08:00
831
7
 ZIP  TAR.GZ
xsn/server_refactor_sleep

0baf73ad96 · should_reset_buckets · Updated 2026-08-19 23:49:59 +08:00
849
11
 ZIP  TAR.GZ
xsn/ggml_rope_off_rest

2dbbb34514 · rm inplace optimization · Updated 2026-08-19 20:07:39 +08:00
845
2
 ZIP  TAR.GZ
xsn/ggml_rope_off

6415eeef12 · Merge branch 'master' into xsn/ggml_rope_off · Updated 2026-08-19 16:39:03 +08:00
850
9
 ZIP  TAR.GZ
xsn/mtmd_bitmap_set_mergeable

85dfd2a292 · mtmd: add mtmd_bitmap_set_mergeable · Updated 2026-08-19 07:55:21 +08:00
855
1
 ZIP  TAR.GZ
xsn/server_no_spam_log

2256a051cf · server: (cosmetic) do not print cmd_child_to_router messages · Updated 2026-08-19 07:37:06 +08:00
856
1
 ZIP  TAR.GZ
xsn/server_dedup_cache_model

5fd3e06e2a · server: add dedup-cache-models preset option · Updated 2026-08-19 07:16:10 +08:00
856
1
 ZIP  TAR.GZ
xsn/ggml_rope_off_vk

e3d49edbf4 · remove inplace optimization · Updated 2026-08-19 06:47:45 +08:00
911
9
 ZIP  TAR.GZ
xsn/server_control_inject

9534049d52 · (sip) allow inject messge to generation · Updated 2026-08-18 17:51:30 +08:00
874
1
 ZIP  TAR.GZ
xsn/server_disk_cache

5234b9d267 · demo, wip · Updated 2026-08-18 06:43:50 +08:00
877
1
 ZIP  TAR.GZ
xsn/vendor_hash_mtmd

15eeceabcb · void conflict with boringssl · Updated 2026-08-18 02:02:56 +08:00
883
2
 ZIP  TAR.GZ
xsn/server_use_mtmd_placeholder

363b198ad4 · server: save processed mtmd chunks as placeholder · Updated 2026-08-18 01:39:51 +08:00
884
1
 ZIP  TAR.GZ
xsn/vendor_hash

992368d6cf · group hashes into one single static lib · Updated 2026-08-17 21:26:16 +08:00
885
2
 ZIP  TAR.GZ
xsn/ui_get_datetime

f990aa7065 · server: drop the now unused ctime include · Updated 2026-08-17 20:27:18 +08:00
879
4
 ZIP  TAR.GZ
xsn/ui_get_info

a27cf9ce2f · Update tools/ui/src/lib/stores/tools.svelte.ts · Updated 2026-08-17 19:06:33 +08:00
880
4
 ZIP  TAR.GZ
xsn/preprocessor_granite_harden

49a5623688 · simply cap to 1024 · Updated 2026-08-17 17:10:53 +08:00
883
2
 ZIP  TAR.GZ
xsn/convert_test

fe48425719 · convert: add test_convert.py · Updated 2026-08-17 17:07:16 +08:00
882
1
 ZIP  TAR.GZ
xsn/convert_add_example

b4e5d8b616 · rm pocket-tts · Updated 2026-08-17 16:14:14 +08:00
885
6
 ZIP  TAR.GZ
gg/test-tag

04a134c70b · ci : make release workflows use a deply key · Updated 2026-08-17 14:58:11 +08:00
886
1
 ZIP  TAR.GZ
xsn/convert_refactor_moe

051139f511 · conversion: refactor moe exp tensor handling · Updated 2026-08-17 07:54:08 +08:00
891
1
 ZIP  TAR.GZ