Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

TP: fix granularity for Qwen 3.5/3.6 + 3 GPUs (#23843)
Johannes Gäßler committed 5 months ago
8b0e0db
2d9b7c8
e674b12
ci : update ios-xcode release job to macos-26 (#23906)
Georgi Gerganov committed 5 months ago
4c4e91b
ggml : add some lsx support (#23798)
Jinyang He committed 5 months ago
d48a56e
ci : fix s390x release job (#23898)
Georgi Gerganov committed 5 months ago
3375285
d4204b0
1738129
0821c5f
ggml-webgpu: add q4_0/q8_0 SET_ROWS (#23760)
Reese Levine committed 5 months ago
b22da25
app: add llama update self updater (#23865)
Pascal committed 5 months ago
5a46b46
22d66b5
vocab : support tokenizer for LFM2.5-8B-A1B (#23826)
Tarek Dakhran committed 5 months ago
2084434
graph : ensure DS32 kq_mask_lid is F32 (#23864)
Sigbjørn Skjæret committed 5 months ago
764f1e6
server: remove obsolete scripts (#23870)
Xuan-Son Nguyen committed 5 months ago
b5f5228
ci : update macos release to use macos-26 runner (#23878)
Georgi Gerganov committed 5 months ago
dc71236
download: add option to skip_download (#23059)
Xuan-Son Nguyen committed 5 months ago
06d26df
mtmd: Add DeepSeekOCR 2 Support (#20975)
Saba Fallah committed 5 months ago
da3f990
server: bump timeout to 3600s (#23842)
Xuan-Son Nguyen committed 5 months ago
cb47092
llama: use f16 mask for FA to save VRAM (#23764)
Aman Gupta committed 5 months ago
031ddb2
sync : ggml
Georgi Gerganov committed 5 months ago
fe12e42
ggml : bump version to 0.13.1 (ggml/1523)
Georgi Gerganov committed 5 months ago
ea02bc3
ngram-mod : Add missing include (#23857)
Omid Azizi committed 5 months ago
b000431
llama: add llm_graph_input_mtp (#23643)
Aman Gupta committed 5 months ago
eef59a7