Grok-1 AWQ - Githubissues

mit-han-lab / llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

MIT License

2.38k stars 184 forks source link

Open jjovalle99 opened 6 months ago

jjovalle99 commented 6 months ago

This is probably a dumb question, but can one quantize Grok-1 using AWQ? If so, what hardware is needed for that?