squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Add float16 and float32 (#1115)

Browse Source
This commit is contained in:
Woosuk Kwon 2023-09-21 00:52:47 -07:00 committed by GitHub
parent 2ac4d5e2bf
commit 1ac4ccf73c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/engine/arg_utils.py
View File

@ -93,7 +93,9 @@ class EngineArgs:
'--dtype', '--dtype',
type=str, type=str,
default=EngineArgs.dtype, default=EngineArgs.dtype,
choices=['auto', 'half', 'bfloat16', 'float'], choices=[
'auto', 'half', 'float16', 'bfloat16', 'float', 'float32'
],
help='data type for model weights and activations. ' help='data type for model weights and activations. '
'The "auto" option will use FP16 precision ' 'The "auto" option will use FP16 precision '
'for FP32 and FP16 models, and BF16 precision ' 'for FP32 and FP16 models, and BF16 precision '