This website works better with JavaScript
Accueil
Explorer
Aide
Connexion
cturan
/
llama.cpp
miroir de
https://github.com/cturan/llama.cpp
Suivre
1
Voter
0
Fork
0
Fichiers
Tickets
0
Wiki
Aborescence:
5d1830b99d
Branches
Tags
k2v2
master
minimax
qwen3_next
qwen3_next_optimized
toolinjection
test
b6814
Historique des commits
Trouver
Auteur
SHA1
Message
Date
Howard Su
bb051d9723
opencl : no need to allocate cl_mem on heap (
#1612
)
il y a 2 ans
Howard Su
ca74884f66
opencl : use strstr to check if fp16 supported (
#1611
)
il y a 2 ans
Maarten ter Huurne
7d873811f3
Fix handling of "invalid property" when creating OpenCL command queue (
#1565
)
il y a 2 ans
0cc4m
2e6cd4b025
OpenCL Token Generation Acceleration (
#1459
)
il y a 2 ans