Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

feat: add GLM5Next MTP, optimize (#29928)
Piotr Wilkin (ilintar) committed 1 month ago
b9acf13
vocab : add plamo fim tokens (#30090)
Sigbjørn Skjæret committed 1 month ago
42b021b
7481354
ad21565
vendor : update cpp-httplib to 0.60.0 (#30081)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 1 month ago
b7dafa0
d2a79e6
sycl : fattn_kv_buffers cleanup (#27689)
Pratyush Kumar committed 1 month ago
5e5b628
vulkan: fix amd iGPU slow checkpoint read (#30049)
Ruben Ortlam committed 1 month ago
4d756bc
sycl: add IQ3_S multi-column MMVQ (#29500)
Clemens Wasser committed 1 month ago
78651c4
f498f86
cuda : add BF16 support for XIELU (#29955)
qiao_px committed 1 month ago
5ad1c5d
4625240
4fbc76d
2207c8e
RPC: add `-sm tensor` (#26610)
Aman Gupta committed 1 month ago
a46709b
cuda: BF16/FP16 conversion to f32 chunking (#29442)
thelittlefireman committed 1 month ago
ab09ea4
models: support pplx-decider (#30044)
Xuan-Son Nguyen committed 1 month ago
da263e7