kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][fix] Fix the error where checkpoint_dir is assigned as NONE wh… (#8401)

Browse Source 
Signed-off-by: maoge <maoge23@qq.com>
Co-authored-by: maoge <maoge23@qq.com>
This commit is contained in:
chinamaoge 2025-10-16 13:37:43 +08:00 committed by GitHub
parent 0a0159fdd8
commit ee588a73ac
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 16 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
tensorrt_llm/_torch/model_config.py
View File

@ -414,16 +414,23 @@ class ModelConfig(Generic[TConfig]):
# Use file lock to prevent race conditions when multiple processes
# try to import/cache the same remote model config file
with config_file_lock():
pretrained_config = transformers.AutoConfig.from_pretrained(
checkpoint_dir,
trust_remote_code=trust_remote_code,
)
# When handling the case where model_format is TLLM_ENGINE
# send cyclic requests to the NONE URL.
if checkpoint_dir is not None:
pretrained_config = transformers.AutoConfig.from_pretrained(
checkpoint_dir,
trust_remote_code=trust_remote_code,
)
# Find the cache path by looking for the config.json file which should be in all
# huggingface models
model_dir = Path(
transformers.utils.hub.cached_file(checkpoint_dir,
'config.json')).parent
# Find the cache path by looking for the config.json file which should be in all
# huggingface models
model_dir = Path(
transformers.utils.hub.cached_file(checkpoint_dir,
'config.json')).parent
else:
raise ValueError(
"checkpoint_dir is None. Cannot load model config without a valid checkpoint directory."
)
quant_config = QuantConfig()
layer_quant_config = None