-
### System Info
- TensorRT-LLM v0.9.0
- Nvidia A10G
### Who can help?
@Tracin
### Information
- [X] The official example scripts
- [ ] My own modified scripts
### Reproduction
…
-
Hello,
Is it any plan to release GPTQ Int8 quantized of 110B model?
Thanks for the Qwen1.5 open source great job!
-
### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答？ | Is there an existing ans…
anyiz updated
6 months ago
-
OCRmyPDF is really marvelous! Thanks!
I have one question regarding output file size: Unless explicitly selecting pdf as output type, I have quite large file sizes (~4x) after "ocrmypdf in.pdf out.…
-
In the docs, it says that when quantizing to anything other than int8, many operations will fall back to fp32.
However, looking through the code (and inserting some print lines) it seems like it ac…
-
Hey, it's me again! 😆 I've done testing on the HQQ pre-trained model inside the Linux system, and it is working well with the custom transformer code you gave me. Now, I want to test the quantization …
-
## Quick summary
running this code
```python…
0BAB1 updated
1 month ago
-
Hello, it seems there's a [
-
### 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…
-