kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-26 06:10:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
9,805 Commits 605 Branches 6,670 Tags

Default Branch

master

f818065d75 · CUDA: batch out_prod broadcast (dps2>1) path with cublasSgemmBatched (#24426) · Updated 2026-06-26 05:51:25 +00:00
 ZIP  TAR.GZ

Branches

0cc4m/vulkan-device-cpy-benchmark

f36e2ab022 · add reverse order tests for dmabuf · Updated 2026-05-21 12:44:52 +00:00    kanshan

531
9
 ZIP  TAR.GZ
gg/gdn-optimize

aa27b85ecf · metal : optimize pad · Updated 2026-05-19 17:17:14 +00:00    kanshan

570
1
 ZIP  TAR.GZ
0cc4m/vulkan-repack

938872e93f · fix partial writes · Updated 2026-05-15 14:00:57 +00:00    kanshan

644
10
 ZIP  TAR.GZ
gg/metal-gdn-partial-rollback

6eb6d84e46 · metal: add GDN partial rollback · Updated 2026-05-14 07:24:09 +00:00    kanshan

674
12
 ZIP  TAR.GZ
gg/spec-mtp-experiments

c8f8e2364c · cont : simplify · Updated 2026-05-11 07:54:07 +00:00    kanshan

741
38
 ZIP  TAR.GZ
gg/spec-refactor-ctx

efa2f8e5a7 · naming : improve consistency · Updated 2026-05-08 09:24:57 +00:00    kanshan

741
24
 ZIP  TAR.GZ
maxk/sched-debug-use-op-desc

ba72d4d287 · ggml: update SCHED_DEBUG output to use ggml_op_desc() · Updated 2026-05-07 23:52:20 +00:00    kanshan

738
1
 ZIP  TAR.GZ
gg/llama-extract-embeddings

0445829c1d · llama : enable layer input extraction · Updated 2026-05-05 17:50:20 +00:00    kanshan

768
1
 ZIP  TAR.GZ
pr/18039-gg

f84632951a · wip · Updated 2026-05-05 06:36:07 +00:00    kanshan

776
23
 ZIP  TAR.GZ
gg/arg-silence-warnings

82af405161 · arg : silence warnings about removed params · Updated 2026-05-04 07:07:57 +00:00    kanshan

788
1
 ZIP  TAR.GZ
sync-ggml-26-05-02

81eabb4781 · sync : ggml · Updated 2026-05-02 05:53:10 +00:00    kanshan

803
2
 ZIP  TAR.GZ
gg/spec-ckpt-test

9d5887035f · testing · Updated 2026-04-30 16:18:57 +00:00    kanshan

817
2
 ZIP  TAR.GZ
gg/pi-gh-tool-rule

6eddb1c6e3 · pi : add rule to use gh CLI for GitHub resources · Updated 2026-04-30 06:49:54 +00:00    kanshan

820
2
 ZIP  TAR.GZ
gg/metal-implement-async-2d

c6a04cb5c3 · ggml-metal: fix 2D async copy to use row-by-row transfers · Updated 2026-04-29 11:57:48 +00:00    kanshan

830
3
 ZIP  TAR.GZ
gg/download-prefer-q8

fd6f79c7a4 · download : prefer q8_0 when q4_k not available · Updated 2026-04-27 09:08:25 +00:00    kanshan

859
1
 ZIP  TAR.GZ
pr/22340-gg

cb9fc575e4 · common : use pimpl in debug.h to reduce header dependencies · Updated 2026-04-26 06:49:28 +00:00    kanshan

880
3
 ZIP  TAR.GZ
opt_arc770_q4_0

b9421898b6 · add for Q4_0 · Updated 2026-04-23 07:33:19 +00:00    kanshan

1022
2
 ZIP  TAR.GZ
0cc4m/server-router-fix-reload-deadlock

a5355a0226 · server: keep router model refcount to avoid unloading models that have running requests · Updated 2026-04-22 08:07:13 +00:00    kanshan

935
15
 ZIP  TAR.GZ
gg/server-remove-api

35df147d80 · cont : remove /api/tags · Updated 2026-04-20 12:45:42 +00:00    kanshan

950
2
 ZIP  TAR.GZ
copilot/plan-semantic-versioning-libllama

4943e3a396 · gen-libllama-abi: compile sort-key regex once outside the lambda · Updated 2026-04-15 12:04:44 +00:00    kanshan

1005
4
 ZIP  TAR.GZ