Skip to content

Tags: JamePeng/llama-cpp-python

Tags

v0.3.16-cu128-AVX2-win-20250913

Toggle v0.3.16-cu128-AVX2-win-20250913's commit message 
Simplify the code structure of test.yaml

v0.3.16-cu128-AVX2-linux-20250913

Toggle v0.3.16-cu128-AVX2-linux-20250913's commit message 
Simplify the code structure of test.yaml

v0.3.16-cu126-AVX2-win-20250913

Toggle v0.3.16-cu126-AVX2-win-20250913's commit message 
Simplify the code structure of test.yaml

v0.3.16-cu126-AVX2-linux-20250913

Toggle v0.3.16-cu126-AVX2-linux-20250913's commit message 
Simplify the code structure of test.yaml

v0.3.16-cu124-AVX2-win-20250913

Toggle v0.3.16-cu124-AVX2-win-20250913's commit message 
Simplify the code structure of test.yaml

v0.3.16-cu124-AVX2-linux-20250913

Toggle v0.3.16-cu124-AVX2-linux-20250913's commit message 
Simplify the code structure of test.yaml

v0.3.16-cu128-AVX2-win-20250831

Toggle v0.3.16-cu128-AVX2-win-20250831's commit message 
Sync llama: use FA + max. GPU layers by default

v0.3.16-cu128-AVX2-linux-20250831

Toggle v0.3.16-cu128-AVX2-linux-20250831's commit message 
Sync llama: use FA + max. GPU layers by default

v0.3.16-cu126-AVX2-win-20250831

Toggle v0.3.16-cu126-AVX2-win-20250831's commit message 
Sync llama: use FA + max. GPU layers by default

v0.3.16-cu126-AVX2-linux-20250831

Toggle v0.3.16-cu126-AVX2-linux-20250831's commit message 
Sync llama: use FA + max. GPU layers by default