Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Maximilian Salén
Magzimilian
3
2
1
Follow
HannesVonEssen's profile picture
21world's profile picture
abbaselmas's profile picture
3 followers
·
2 following
MaximilianSalen
AI & ML interests
None yet
Recent Activity
updated
a model
about 18 hours ago
embedl/Alpamayo2-Edge
updated
a model
15 days ago
embedl/rf-detr-base-quantized-tensorrt
new
activity
15 days ago
embedl/rf-detr-base-quantized-tensorrt:
PyTorch .pt2 matching the TensorRT 10 ONNX (projector+decoder unquantized, re-calibrated backbone); PyTorch COCO 52.35 vs FP32 53.30
View all activity
Organizations
Magzimilian
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
embedl/rf-detr-base-quantized-tensorrt
15 days ago
PyTorch .pt2 matching the TensorRT 10 ONNX (projector+decoder unquantized, re-calibrated backbone); PyTorch COCO 52.35 vs FP32 53.30
#2 opened 15 days ago by
Magzimilian
New activity in
embedl/rf-detr-base-quantized-tensorrt
16 days ago
TensorRT 10 fix: opset 19 (GridSample bilinear), FP16 decoder+projector, re-calibrated backbone; Jetson TensorRT accuracy and speed
#1 opened 16 days ago by
Magzimilian
New activity in
embedl/dinov3-quantized-tensorrt
3 months ago
How to reproduce this ONNX with the public PyPI embedl-deploy 0.8.1?
3
#2 opened 3 months ago by
Jonnas0919