Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

sync : ggml
Georgi Gerganov committed 4 months ago
7d56da7
ggml : bump version to 0.17.0 (ggml/1568)
Georgi Gerganov committed 4 months ago
3727404
635cdd5
11fd0a6
vulkan: Support Q2_0 (#25430)
Jeff Bolz committed 4 months ago
788e07d
opencl: add ABS op (#25115)
Gezahegne committed 4 months ago
b85833e
DeepseekV4: Add fused hyper-connection ops (#25585)
Aman Gupta committed 4 months ago
0dc74e3
f15bd60
conversion: accept BitNetForCausalLM architecture name (#25769)
Khashayar Ghafouri committed 4 months ago
3278e92
TP: fix Phi3, Bert, Plamo2/3, ChatGLM (#25536)
Johannes Gäßler committed 4 months ago
2e1fd76
vendor: update BoringSSL to 0.20260713.0 (#25624)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 4 months ago
86b719b
CUDA: Support CUDA Virtual Devices (#25228)
Anav Prasad committed 4 months ago
79bba02
Enable CUDA graphs on volta+turing (#25749)
Alexander Heisler committed 4 months ago
3f08ef2
8ee54c8
c7d8722
CUDA: dedup MoE gate/up activation quantization (#25441)
Pranesh Gonegandla committed 4 months ago
5839ba3
ci : add official website link to release notes (#25728)
Georgi Gerganov committed 4 months ago
a320cbf
56d6e9d