Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
kernels-community
/
quantization
like
0
Follow
kernels-community
9
License:
apache-2.0
Model card
Files
Files and versions
Community
main
quantization
/
fp8
1 contributor
History:
2 commits
danieldk
HF staff
Sync with vLLM
0da5bf5
27 days ago
amd
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
2 months ago
nvidia
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
2 months ago
common.cu
Safe
5.71 kB
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
2 months ago
common.cuh
Safe
5.63 kB
Sync with vLLM
27 days ago
fp8_marlin.cu
Safe
51.1 kB
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
2 months ago
