Prince Canuma
@prince-canuma.bsky.social
Thanks for the warm welcome, Ken!
November 27, 2024 at 3:43 AM
Thanks for the warm welcome, Ken!
@hugg Idefics 3 and SmolVLM now on MLX 🎉🚀
You can now run inference and fine-tune locally on your Mac.
pip install -U mlx-vlm
I’m getting ~140 tok/s on M3 Max 96GB 🔥
Thanks to @pcuenq.hf.co for PR!
Model Cards 👇🏽
You can now run inference and fine-tune locally on your Mac.
pip install -U mlx-vlm
I’m getting ~140 tok/s on M3 Max 96GB 🔥
Thanks to @pcuenq.hf.co for PR!
Model Cards 👇🏽
November 26, 2024 at 11:07 PM
Up next 🚧:
- Major refactoring
- Run language model only
- Image / Video feature + prompt caching
- Batch Inference
- KV quantization
- KV cache with attention sinks
- Full FT
- Lora Adapter merging
- New Models
- Major refactoring
- Run language model only
- Image / Video feature + prompt caching
- Batch Inference
- KV quantization
- KV cache with attention sinks
- Full FT
- Lora Adapter merging
- New Models
November 24, 2024 at 5:29 PM
Up next 🚧:
- Major refactoring
- Run language model only
- Image / Video feature + prompt caching
- Batch Inference
- KV quantization
- KV cache with attention sinks
- Full FT
- Lora Adapter merging
- New Models
- Major refactoring
- Run language model only
- Image / Video feature + prompt caching
- Batch Inference
- KV quantization
- KV cache with attention sinks
- Full FT
- Lora Adapter merging
- New Models