Feed Apps Remote

Appgithub-com-ggerganov-llama-cpp

Download Pinokio

Sign in Create accountJoin

Sign in Create accountJoin

llama.cpp

github.com/ggerganov/llama.cppUpdated 6mo ago

LLM inference in C/C++

Loading community details…

Loading project owner…

Loading launchers…

Loading check-ins…

Community

Sort byCreate post

Ask or share about llama.cpp…

Loading...

Loading references…

Loading project activity…

Pinokio

Feed Apps Remote

0

Available launchers4

llamacppgithub.com/cocktailpeanut/llamacpp.pinokiogit clone in install/bin/install.json2 check-ins · updated 1y ago · Project owner @cocktailpeanut

LocalAI Chatbotgithub.com/vtomasv/localai-chatbot-pinokiogit clone in install/bin/install.json0 check-ins · updated 8mo ago

Mirrorgithub.com/cocktailpeanut/mirrorgit clone in install.json0 check-ins · updated 2y ago · Project owner @cocktailpeanut

Check-ins (0)

Recent commits

Fix for issue #22974. Cast intermediate results to float before adding and casting the result to the destination type. Avoids half+half operator ambiguity. (#22994)

scutler-nv6 months ago7f3f843

server, webui: accept continue_final_message flag for vLLM API compat (#23012)

Pascal6 months ago95d469a

docs : Update OPENVINO.md (#22959)

Ravi Panchumarthy6 months ago7e16646

webui: Deduplicate model aliases in data + handle single/multiple aliases in UI (#22979)

Aleksander Grygier6 months ago2dfeca3

webui: preserve system message on edit cancel (#22911)

Pascal6 months ago46be24d

ggml-webgpu: only use subgroup-matrix path when head dims are divisible by sg_mat_k / sg_mat_n (#23020)

Zheyuan Chen6 months ago4c1c3ac

opencl: add q5_0 and q5_1 MoE for Adreno (#22985)

shaofeiqi6 months agoec562eb

opencl: fix crash when warming up MoE on Adreno (#22876)

lhez6 months ago1e4579f

flush the gpu profile timestamp before the queryset is overflowed (#22995)

Masashi Yoshimura6 months ago527045b

hexagon: add unary tanh op (#22999)

Max Krasnyansky6 months agoad96bb8