3 Commits

Author	SHA1	Message	Date
Ettore Di Giacinto	2c8623dbb4	fix(python): move vllm to after deps, drop diffusers main deps ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-08-07 23:34:37 +02:00
Ettore Di Giacinto	11b2adae0c	fix(vllm): drop flash-attn installation afterwards ... Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>	2024-08-07 18:08:26 +02:00
Ettore Di Giacinto	61b5602111	fix(python): move accelerate and GPU-specific libs to build-type (#3194) ... Some of the dependencies in `requirements.txt`, even if generic, pulls down the line CUDA libraries. This changes moves mostly all GPU-specific libs to the build-type, and tries a safer approach. In `requirements.txt` now are listed only "first-level" dependencies, for instance, grpc, but libs-dependencies are moved down to the respective build-type `requirements.txt` to avoid any mixin. This should fix #2737 and #1592. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-08-07 17:02:32 +02:00