proxy.golang.org : github.com/intel/neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Registry
-
Source
- Documentation
- JSON
- codemeta.json
purl: pkg:golang/github.com/intel/neural-compressor
Keywords:
auto-tuning
, awq
, fp4
, gptq
, int4
, int8
, knowledge-distillation
, large-language-models
, low-precision
, mxformat
, post-training-quantization
, pruning
, quantization
, quantization-aware-training
, smoothquant
, sparsegpt
, sparsity
License: Apache-2.0
Latest release: 29 days ago
First release: almost 5 years ago
Stars: 2,512 on GitHub
Forks: 281 on GitHub
Total Commits: 3588
Committers: 125
Average commits per author: 28.704
Development Distribution Score (DDS): 0.908
More commit stats: commits.ecosyste.ms
See more repository details: repos.ecosyste.ms
Last synced: 1 day ago