huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Automatic quantization config.

Browse Source
This commit is contained in:
Nicolas Patry 2024-04-09 05:40:52 +00:00
parent ff42d33e99
commit fd536f2017
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
server/text_generation_server/models/__init__.py
View File

@ -186,6 +186,14 @@ def get_model(
raise RuntimeError( raise RuntimeError(
f"Could not determine model type for {model_id} revision {revision}" f"Could not determine model type for {model_id} revision {revision}"
) )
quantization_config = config_dict.get("quantization_config", None)
if quantization_config is not None and quantize is None:
method = quantization_config.get("quant_method", None)
if method in {"gptq", "awq"}:
logger.info(f"Auto selecting quantization method {method}")
quantize = method
else:
logger.info(f"Unknown quantization method {method}")
if model_type == "ssm": if model_type == "ssm":
return Mamba( return Mamba(