vllm-project / llm-compressor

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Apache License 2.0
407 stars 29 forks source link

compressed-tensors main dependency for base-tests #125

Closed kylesayrs closed 2 weeks ago

kylesayrs commented 2 weeks ago

SUMMARY:

TEST PLAN: