Yang Hao

[Bug] internvl2-2b使用awq量化后，推理速度基本上没有提升，精度还掉点

4

### Checklist - [ ] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest...

[Bug] internvl2-2B awq w4a16量化后掉点严重，应该如何排查？

2

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version. -...

[Bug] 为什么minicpm-v2_5 使用awq int4量化后速度比fp16慢三倍

9

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. -...

stack during import tensorrt_llm

3

### System Info - CPU x86_64 - GPU: L40 - tensorrt_llm: 0.11.0 - CUDA: 12.4 - driver: 535.129.03 - OS: CentOS 7 ### Who can help? When I tried to...

Does compiling Decord from source depend on FFmpeg?

1

Hi Decord team, Does compiling Decord from source depend on FFmpeg, or is FFmpeg required only for compiling the CUDA version of Decord? When I enabled CUDA compilation, the following...