LMM

Results 6 issues of LMM

多输入为有不同的shape,2/3/4维都有,请问这个QAT范式支持吗?如果支持的话,在保存模型前的一次前向推理应该怎么写呢?如官方给出的example: predict = net.forward(F.placeholder([1, 3, 224, 224], F.NC4HW4)) 那么请问我这个多输入的应该怎么写吗?我尝试按照net的输入顺序一次填入,执行失败了(没有报错),结果出现很多print出来是很多array~,求教

您好,感谢你的分享,我现在想复现您的工作,但是目前v1/v2两个版本的4个模型下载链接都失效,请问你是更新了地址吗?还是?求正确的链接~

hi! thanks for your repo,can you show the bleu for this repo on WMT14 dataset?

cpu: x86_64 gpu: nvidia H20 cuda version: 12.4 tensorrt-llm version: 0.14.0 I follow https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/qwen/README.md running qwen2 0.5B model, The results I obtained are as follows: * case0 with code: *...

**Description** I am using CUDA 12.2 and would like to know the highest version of TensorRT-LLM that I can install. Can you please provide information on compatibility? **My Environment:** -...

question
not a bug