Skip to content
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

Fix fp16 (--half) support for TritonRemoteModel model type #10787

Merged
merged 4 commits into from
May 16, 2023
Merged

Fix fp16 (--half) support for TritonRemoteModel model type #10787

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
83a2a01
Fix fp16 (--half) support for TritonRemoteModel
fabito Jan 18, 2023
0984f6f
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jan 18, 2023
c9904f3
Merge branch 'master' into bugfix/triton-half-precision
fabito Mar 29, 2023
11e6ef1
Merge branch 'master' into bugfix/triton-half-precision
glenn-jocher May 16, 2023
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
Next Next commit
Fix fp16 (--half) support for TritonRemoteModel
  • Loading branch information
@fabito
fabito committed Jan 18, 2023
commit 83a2a01ff948a47a20740db8ea487159a22356d7
2 changes: 1 addition & 1 deletion models/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -334,7 +334,7 @@ def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False,
super().__init__()
w = str(weights[0] if isinstance(weights, list) else weights)
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, triton = self._model_type(w)
fp16 &= pt or jit or onnx or engine # FP16
fp16 &= pt or jit or onnx or engine or triton # FP16
nhwc = coreml or saved_model or pb or tflite or edgetpu # BHWC formats (vs torch BCWH)
stride = 32 # default stride
cuda = torch.cuda.is_available() and device.type != 'cpu' # use CUDA
Expand Down