Robert IrvineandRobert Irvine 4b5bcf8906 faster startup of vLLM (#982) ...

* update

---------

Co-authored-by: Robert Irvine <robert@seamlessml.com>

2023-09-08 14:48:54 +09:00

..

layers

faster startup of vLLM (#982)

2023-09-08 14:48:54 +09:00

models

Enable safetensors loading for all models (#974)

2023-09-07 15:49:52 -07:00

parallel_utils

Add Falcon support (new) (#592)

2023-08-02 14:04:39 -07:00

__init__.py

[Quality] Add code formatter and linter (#326)

2023-07-03 11:31:55 -07:00

input_metadata.py

Add support for BLOOM (#331)

2023-07-03 13:12:35 -07:00

model_loader.py

Enable safetensors loading for all models (#974)

2023-09-07 15:49:52 -07:00

utils.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

weight_utils.py

Enable safetensors loading for all models (#974)

2023-09-07 15:49:52 -07:00