An LLM and VLM post-training quantization toolkit from Intel that compresses models to low-bit weights for Transformers, vLLM and SGLang.
1.7K193PythonApache-2.0Updated 4 hours ago
#post-training-quantization
Open-source projects tagged “post-training-quantization”
Curated GitHub repositories related to post-training-quantization, with AI summaries and key stats.