cccpr

imagenet训练代码可以公布吗？

2

imagenet训练代码可以公布吗？

error when using tensorboard with crayon: ValueError: The server at 127.0.0.1:8889 does not appear to be up!

6

I just run: jcc@jcc:/ground/faster_rcnn_pytorch$ sudo docker pull alband/crayon [sudo] password for jcc: latest: Pulling from alband/crayon 96a1ef3ccac0: Already exists 2415c9cbee29: Already exists 285141620f12: Already exists cdc8a9d219b0: Already exists c6fe6b5c116d: Already...

In this vit training log, it only took 18 hours to train vit model on imagenet for as long as 300 epoches, I want to know the training details

1

### Branch main branch (mmpretrain version) ### Describe the bug https://download.openmmlab.com/mmclassification/v0/vit/vit-base-p16_pt-32xb128-mae_in1k_20220623-4c544545.log ### Environment https://download.openmmlab.com/mmclassification/v0/vit/vit-base-p16_pt-32xb128-mae_in1k_20220623-4c544545.log ### Other information In this vit training log, it only took 18 hours to train vit...

How to do clean model.forward() with tensor input and tensor output with TensorRT-LLM?

4

similar issue here: https://github.com/NVIDIA/TensorRT-LLM/issues/158 The ModelRunner defined [here](https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/runtime/generation.py) seems to only have a `generate `function, which includes so many complicated operations defined here: https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/runtime/generation.py , with no clean `model.forward()` What...

llama2-7b bad results for int8-kv-cache + per-channel-int8-weight

18

### System Info 3090 gpu 0.7.1 tensorrt-llm ### Who can help? _No response_ ### Information - [ ] The official example scripts - [ ] My own modified scripts ###...

general question about SmoothQuant kv-cache quantization

1

1. Is kv-cache actually **not used** in all the LLM-evaluation tasks, since those tasks usually takes **only one-step** attention calculation, not like language generating process which needs a lot of...

### 📚 The doc issue 问lmdeploy中的w8a8-triton实现是否有 实际llm（如llama2，qwen2）的推理速度加速效果的benchmark测试？ ### Suggest a potential alternative/fix 问lmdeploy中的w8a8-triton实现是否有 实际llm（如llama2，qwen2）的推理速度加速效果的benchmark测试？