Skip to content

fix: add dtype config option to VllmArgs for older GPU support #212

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
octo-patch wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix: add dtype config option to VllmArgs for older GPU support #212

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
68c602d
fix: add dtype config option to VllmArgs for older GPU support (fixes…
Apr 19, 2026
990e002
fix: constrain VllmArgs.dtype to vLLM-supported Literal values
Apr 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion settings.template.jsonc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,8 +91,9 @@
},
"vllm_args": {
"gpu_memory_utilization": 0.9,
// "dtype": "float16", // For GPUs with compute capability < 8.0 (e.g., Tesla T4, V100) that don't support bfloat16
// "data_parallel_size": 2,
// "quantization": "bitsandbytes",
// "quantization": "bitsandbytes",
// "load_format": "bitsandbytes"
},
"test_model_args": {
Expand Down
7 changes: 7 additions & 0 deletions weclone/utils/config_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,6 +207,13 @@ class InferArgs(BaseConfigModel):

class VllmArgs(BaseConfigModel):
gpu_memory_utilization: float = Field(default=0.9, description="vllm GPU memory utilization")
dtype: Optional[str] = Field(
default=None,
description=(
"Data type for vLLM inference. Set to 'float16' for GPUs with compute capability < 8.0 "
"(e.g., Tesla T4, V100) that do not support bfloat16."
),
)
Comment thread
sourcery-ai[bot] marked this conversation as resolved.
Outdated


class TestModelArgs(BaseConfigModel):
Expand Down