Code & Deploy
siGit Code
Git Hosting
Toggle menu
siGit Code
Git Hosting
Sign in
Sign in
@tduncan
/
Nvidia-Optimization-Stack-VLLM
Nvidia-Optimization-Stack-VLLM
/
csrc
/
libtorch_stable
/
quantization
/
marlin
Code
Commits
Issues
Pulls
Cloud Agent
CI/CD
main
main
.gitignore
awq_marlin_repack.cu
dequant.h
generate_kernels.py
gptq_marlin_repack.cu
kernel.h
marlin.cu
marlin.cuh
marlin_dtypes.cuh
marlin_int4_fp8_preprocess.cu
marlin_mma.h
marlin_template.h