-
**YOLOv9 with Quantization-Aware Training (QAT) for TensorRT**
https://github.com/levipereira/yolov9-qat/
This repository hosts an implementation of YOLOv9 integrated with Quantization-Aware Train…
-
The Ollama model hub still has the default quant type of Q4_0 which is a legacy format that under-performs compared to K-quants (Qn_K, e.g. Q4_K_M, Q6_K, Q5_K_L etc...).
- Would it perhaps make sen…
-
### Report of performance regression
Hi I use this:
```
server_vllm.py \
--model "/data/models_temp/functionary-small-v2.4/" \
--served-model-name "functionary" \
--dtype=bfloat16 \
-…
rvsh2 updated
2 weeks ago
-
## Description
Model conversion process failed with djl-tensorrtllm and below serving.properties:
```
image_uri = image_uris.retrieve(
framework="djl-tensorrtllm",
region=sess…
-
Since We adopt per-tensor quantization for activation and per-channel quantization for weight, I am confused that why the the entries in a_scale tensor at line 230 not share the same value, I suppos…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and f…
-
Good night.
EasyOCR is crashing the Python 3.10 VM
Ubuntu 22.04 / Debian Bullseye (identical problem but Python 3.9)
Architecture Raspberry Pi 4 4GBytes
Error as follows:
Python 3.10.12 (ma…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### Ultralytics YOLO Component
…
-
### Branch/Tag/Commit
main
### Docker Image Version
nvcr.io/nvidia/pytorch:23.04-py3
### GPU name
T4
### CUDA Driver
470.141.03
### Reproduced Steps
I'm trying to run `calib…
-
### Describe the issue
The DequantizeLinear, pad, and QuantizeLinear operations in the statically quantized model using the optimization level ORT_ENABLE_EXTENDED are not fused into one operation. My…