huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 16:32:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update model.py

Browse Source 
Pulling from https://github.com/huggingface/optimum-neuron/pull/776
This commit is contained in:
Jim Burtoft 2025-02-26 18:47:33 -05:00 committed by GitHub
parent 5eec3a8bb6
commit 1cb904e619
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
backends/neuron/server/text_generation_server/model.py
View File

@ -107,10 +107,26 @@ def fetch_model(
if not is_cached(model_id, neuron_config): if not is_cached(model_id, neuron_config):
hub_cache_url = "https://huggingface.co/aws-neuron/optimum-neuron-cache" hub_cache_url = "https://huggingface.co/aws-neuron/optimum-neuron-cache"
neuron_export_url = "https://huggingface.co/docs/optimum-neuron/main/en/guides/export_model#exporting-neuron-models-using-neuronx-tgi" neuron_export_url = "https://huggingface.co/docs/optimum-neuron/main/en/guides/export_model#exporting-neuron-models-using-neuronx-tgi"
entries = get_hub_cached_entries(model_id, "inference")
available_configs = ""
if entries:
config_list = []
for entry in entries:
config = (
f"batch_size={entry['batch_size']}, "
f"sequence_length={entry['sequence_length']}, "
f"num_cores={entry['num_cores']}, "
f"auto_cast_type={entry['auto_cast_type']}"
)
config_list.append(config)
available_configs = "\nAvailable cached configurations for this model:\n- " + "\n- ".join(config_list)
else:
available_configs = "\nNo cached versions are currently available for that model with any configuration."
error_msg = ( error_msg = (
f"No cached version found for {model_id} with {neuron_config}." f"No cached version found for {model_id} with {neuron_config}."
f"You can start a discussion to request it on {hub_cache_url}" f"{available_configs}"
f"Alternatively, you can export your own neuron model as explained in {neuron_export_url}" f"\nYou can start a discussion to request it on {hub_cache_url}"
f"\nAlternatively, you can export your own neuron model as explained in {neuron_export_url}"
) )
raise ValueError(error_msg) raise ValueError(error_msg)
logger.warning( logger.warning(