xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 08:04:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix boolean conversion for OpenVINO env variable (#13615)

Browse Source
This commit is contained in:
Helena Kloosterman 2025-02-22 17:04:12 +01:00 committed by GitHub
parent 8354f6640c
commit 382f66fb08
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/envs.py
View File

@ -360,8 +360,9 @@ environment_variables: Dict[str, Callable[[], Any]] = {
# Enables weights compression during model export via HF Optimum
# default is False
"VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS":
lambda: bool(os.getenv("VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS", False)),
lambda:
(os.environ.get("VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS", "0").lower() in
("on", "true", "1")),
# If the env var is set, then all workers will execute as separate
# processes from the engine, and we use the same mechanism to trigger
# execution on all workers.

3
vllm/model_executor/model_loader/openvino.py
View File

@ -125,7 +125,8 @@ class OpenVINOCausalLM(nn.Module):
"as-is, all possible options that may affect model conversion "
"are ignored.")
load_in_8bit = envs.VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS
load_in_8bit = (envs.VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS
if export else False)
pt_model = OVModelForCausalLM.from_pretrained(
model_config.model,
export=export,