Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

kernels-community
/
quantization

kernel
Model card Files Files and versions Community
1
quantization / gptq_marlin
Ctrl+K
Ctrl+K
  • 2 contributors
History: 4 commits
danieldk's picture
danieldk HF Staff
Sync to vLLM 20250627
8aa00a3 8 days ago
  • awq_marlin_repack.cu
    8.8 kB
    Sync to vLLM 20250627 8 days ago
  • dequant.h
    18.6 kB
    Sync to vLLM 20250627 8 days ago
  • generate_kernels.py
    4.39 kB
    Sync to vLLM 20250627 8 days ago
  • gptq_marlin.cu
    35.7 kB
    Sync to vLLM 20250627 8 days ago
  • gptq_marlin_repack.cu
    11.1 kB
    Sync to vLLM 20250627 8 days ago
  • kernel.h
    1.93 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_bf16_kfe2m1f.cu
    2.17 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_bf16_kfe4m3fn.cu
    4.24 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_bf16_ku4.cu
    8.02 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_bf16_ku4b8.cu
    10.1 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_bf16_ku8b128.cu
    10.3 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_fp16_kfe2m1f.cu
    2.06 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_fp16_kfe4m3fn.cu
    4.03 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_fp16_ku4.cu
    9.44 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_fp16_ku4b8.cu
    9.61 kB
    Sync to vLLM 20250627 8 days ago
  • kernel_fp16_ku8b128.cu
    9.76 kB
    Sync to vLLM 20250627 8 days ago
  • marlin.cuh
    2.42 kB
    Sync to vLLM 20250627 8 days ago
  • marlin_dtypes.cuh
    2.1 kB
    Sync to vLLM 20250627 8 days ago
  • marlin_template.h
    67.5 kB
    Sync to vLLM 20250627 8 days ago