mlx-examples/llms/mlx_lm/requirements.txt
Awni Hannun 5cae0a60e6
deepseek v3 model with pipeline parallelism (#1191)
* deepseekv3

* use upload_large_file instead of deprecated multi comit

* add pipeline generation and example

* comment

* get fp16 working

* use mlx==0.22
2025-01-09 15:55:53 -08:00

7 lines
77 B
Plaintext

mlx>=0.22.0
numpy
transformers[sentencepiece]>=4.39.3
protobuf
pyyaml
jinja2