Compress LLMs with FP8, GPTQ & SmoothQuant
New tutorial demonstrates compressing instruction-tuned LLMs using llmcompressor. Compare FP8, GPTQ, and SmoothQuant for…
1 articles about 'llmcompressor'
New tutorial demonstrates compressing instruction-tuned LLMs using llmcompressor. Compare FP8, GPTQ, and SmoothQuant for…