mirrors/llama.cpp
0
0 Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-28 09:45:55 +08:00
Code Activity
11,946 Commits 908 Branches 8,219 Tags

Default Branch

master

8ca4060b7e · server : add realtime conversation and transcription on /v1/realtime (#31269) · Updated 2026-10-28 08:26:12 +08:00
 ZIP  TAR.GZ

Branches

0cc4m/fp8-scaled-mm

9577b2cf79 · Wire activation scales and disallow broadcasting over K · Updated 2026-10-28 01:47:48 +08:00
5
107
 ZIP  TAR.GZ
0cc4m/fp8-scaled-mm-vulkan

8325ee6a19 · fix test issue · Updated 2026-10-28 01:47:48 +08:00
5
111
 ZIP  TAR.GZ
osimons/ocp_fp8_cuda

bb9a2b4b6c · WIP src1/prec for fp8 in MMVF · Updated 2026-10-28 01:47:47 +08:00
5
83
 ZIP  TAR.GZ
osimons/ocp_fp8

7cf892cbb9 · LF line endings · Updated 2026-10-28 01:47:46 +08:00
5
38
 ZIP  TAR.GZ
osimons/ocp_fp8_kv

661dc662d5 · Adjust test label for test-kv-cache.cpp · Updated 2026-10-28 01:47:46 +08:00
5
53
 ZIP  TAR.GZ
rpc_tensor_loading

3a95ed36f6 · cont : release loader staging buffer on shrink · Updated 2026-10-28 01:03:43 +08:00
8
2
 ZIP  TAR.GZ
aman/glm5-next-sm-tensor

49a581a8d4 · glm5-next : drop the q_absorbed cont · Updated 2026-10-28 00:15:19 +08:00
60
6
 ZIP  TAR.GZ
gg/tests-reduce-warnings

d730b3d300 · tests : adjust constants to reduce irrelevant warnings · Updated 2026-10-27 23:22:34 +08:00
9
1
 ZIP  TAR.GZ
gg/ggml-remove-api

d72b42fa7f · ggml : remove public ggml_backend_buffer_copy_tensor() · Updated 2026-10-27 23:01:45 +08:00
9
1
 ZIP  TAR.GZ
gg/ggml-tensor-get-set-n

70a1ba2517 · cont : const correctness · Updated 2026-10-27 22:25:16 +08:00
11
10
 ZIP  TAR.GZ
aman/sparse-unified

86e87218bb · remove the exception for qwen4exp · Updated 2026-10-27 21:59:02 +08:00
10
8
 ZIP  TAR.GZ
allozaur/feat/save-settings-on-changes

b3ea8b63fa · ui : move reset settings button next to reload app, pad settings caption · Updated 2026-10-27 21:01:00 +08:00
21
2
 ZIP  TAR.GZ
gg/glm5

b59c34a5f6 · meta : tmp patch · Updated 2026-10-27 19:34:03 +08:00
15
7
 ZIP  TAR.GZ
gg/glm5-save

b59c34a5f6 · meta : tmp patch · Updated 2026-10-27 19:34:03 +08:00
15
7
 ZIP  TAR.GZ
allozaur/fix/24164-ogg-audio-attachments

648b5c8588 · ui: convert all non WAV/MP3 audio uploads to WAV · Updated 2026-10-27 19:06:00 +08:00
36
2
 ZIP  TAR.GZ
aman/moe-cache-cpu-misses

ae36884b7d · Fix MSVC compilation · Updated 2026-10-27 18:55:25 +08:00
38
7
 ZIP  TAR.GZ
allozaur/fix/system-message-height

4fa35c3022 · ui: fix system message row stretching to full prompt height in WebKit · Updated 2026-10-27 18:26:46 +08:00
20
1
 ZIP  TAR.GZ
codex/model-hf-required-message

69f71faa4c · common : --model or -hf is required · Updated 2026-10-27 17:51:23 +08:00
21
1
 ZIP  TAR.GZ
allozaur/fix/24338-new-chat-draft-deleted-on-system-prompt

5c024cb52d · Merge remote-tracking branch 'origin/master' into allozaur/fix/24338-new-chat-draft-deleted-on-system-prompt · Updated 2026-10-27 14:54:04 +08:00
23
3
 ZIP  TAR.GZ
gg/opt-test-llama-archs

7bf2deb38c · tests : simplify the model save log · Updated 2026-10-27 13:56:45 +08:00
23
4
 ZIP  TAR.GZ