Appgithub-com-abetlen-llama-cpp-python

Download Pinokio

Sign in Create accountJoin

Sign in Create accountJoin

llama-cpp-python

github.com/abetlen/llama-cpp-pythonUpdated 5mo ago

Python bindings for llama.cpp

Loading community details…

Loading project owner…

Loading launchers…

Loading check-ins…

Community

Sort byCreate post

Ask or share about llama-cpp-python…

Loading...

Loading references…

Loading project activity…

Pinokio

0

Available launchers2

AceJAMFeaturedgithub.com/cocktailpeanut/acejam.pinokiopip install from git in install.js13 check-ins · updated 4mo ago · Project owner @cocktailpeanut

ZastTranslate — Beta 1.21github.com/zast57/ZastTranslatepip install from git in install.js4 check-ins · updated 4d ago

Check-ins (0)

Recent commits

feat: update llama.cpp to 5d6f18a63 (#2207)

Andrei6 months agof774690

fix: configure n_seq_max for batched embeddings (#2206)

Andrei6 months ago128c331

fix(_internals): use n_tokens0 offset when enabling last-token logits in add_sequence (#2205)

Tai An6 months ago90e8df9

fix(ci): skip unsupported Windows CUDA versions (#2204)

Andrei6 months ago14d7846

fix(ci): install CUDA CCCL headers for wheel builds (#2203)

Andrei6 months agobc6ff9f

fix(ci): pass CUDA compiler arg for Windows detection (#2202)

Andrei6 months ago04a3638

fix(ci): pass CUDA unsupported compiler flag during detection (#2201)

Andrei6 months ago2bfd80c

chore: bump version to 0.3.22 (#2200)

Andrei6 months ago9cf0ce7

feat(ci): re-enable Windows CUDA wheels (#2198)

Andrei6 months agod2113a1

feat: Update llama.cpp to ggerganov/llama.cpp@63d93d173 (#2197)

Andrei6 months ago587d94a