Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

revert to using global_invocation_id for cpy shader (#23955)
Masashi Yoshimura committed 5 months ago
b8275a8
nix : add nix-nodejs facilities to build Web UI (#23846)
Christian Hoener zu Siederdissen committed 5 months ago
5aa3a64
27d9ed8
vendor : update cpp-httplib to 0.46.1 (#23980)
Adrien Gallouët committed 5 months ago
335abed
de6f727
metal: template GLU kernels to support f16/f32 (#23882)
Shrivas Shankar committed 5 months ago
95b8b8e
vulkan: reduce host memory lock contention (#23376)
Winston Ma committed 5 months ago
bef69f1
TP: quantized KV cache support (#23792)
Johannes Gäßler committed 5 months ago
8e6fff8
security : disable private disclosures (#23963)
Georgi Gerganov committed 5 months ago
02a5701
model: Add EXAONE 4.5 implementations (#21733)
Junwon Hwang committed 5 months ago
48b88c3
vulkan: Removed unused functions (#23175)
Winston Ma committed 5 months ago
f8c0a19
e22b0de
a511424
[SYCL] Add more types in GET_ROWS OP (#23710)
Neo Zhang committed 5 months ago
4162522
sycl : Optimize Q3_K mul_mat by reorder (#23725)
Neo Zhang committed 5 months ago
44e211c
af6528e
server : handle If-None-Match weak ETags (#23916)
Eric Zhang committed 5 months ago
6f165c1
ci : limit trigger paths for the CPU workflow (#23938)
Georgi Gerganov committed 5 months ago
399739d
ui: fix ETag truncation with MSVC compiler (#23917)
Eric Zhang committed 5 months ago
3292da0
docs : update ZenDNN docs for Q8 support (#23791)
Vladislav committed 5 months ago
e6123e2
llama: only use one iGPU device by default (#23897)
Ruben Ortlam committed 5 months ago
22cadc1
d749821
Support `-fa auto` in llama-bench (#23714)
Gaurav Garg committed 5 months ago
aa46bda
d6588da