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

check for non-native models

Browse Source
This commit is contained in:
Cyril Vallez 2025-01-20 18:01:12 +01:00
parent 2ef3002c2b
commit 70ada578b9
No known key found for this signature in database
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
server/text_generation_server/models/__init__.py
View File

@ -16,7 +16,6 @@ from transformers.models.auto import modeling_auto
from huggingface_hub import hf_hub_download, HfApi
from typing import Optional, List, Dict
from pathlib import Path
import transformers
from text_generation_server.utils.speculate import get_speculate, set_speculate
from text_generation_server.models.model import Model
@ -385,11 +384,14 @@ def get_model(
transformers_causal_lm_class = CausalLM
# Fast transformers path
transformers_model_class = getattr(
transformers, modeling_auto.MODEL_FOR_CAUSAL_LM_MAPPING_NAMES[model_type]
transformers_model_class = modeling_auto.MODEL_FOR_CAUSAL_LM_MAPPING_NAMES.get(
model_type, None
)
if FLASH_TRANSFORMERS_BACKEND and transformers_model_class._supports_flex_attn:
if (
FLASH_TRANSFORMERS_BACKEND
and transformers_model_class is not None
and transformers_model_class._supports_flex_attn
):
transformers_causal_lm_class = TransformersFlashCausalLM
quantization_config = config_dict.get("quantization_config", None)