Suggestion: Add Bloom support

FMInference / FlexLLMGen

Running large language models on a single GPU for throughput-oriented scenarios.

Apache License 2.0

9.21k stars 547 forks source link

Open robinsongh381 opened 1 year ago

robinsongh381 commented 1 year ago

I would be great if FlexGen supports Bloom models from huggingface !

merrymercy commented 1 year ago

It is in our roadmap. Contributions are welcome!