Tlntin/Qwen-TensorRT-LLM Issues
triton同步异步接口询问
Updated 10how to build Qwen-72B-Chat-Int4 with tp=2
Updated 16测试hf吞吐OOM以及triton并发、流式输出问题
Closed 21请问如何支持正常的batch infer ？
Closed 2请问为什么smoothquant量化后显存占用不降低呢
Closed 6大佬有没有对比和VLLM的推理效果？
UpdatedQwen-72B-Chat-Int4 killed
Closed 1Qwen1.5 GPTQ用不了
Closed 2Qwen1.5 GPTQ-Int4 编译失败
Closed 15Qwen1.5 GPTQ编译错误
Closed 1Qwen2 编译错误
Closed 5Qwen-72B有遇到输入超过2048以后返回有问题的情况吗
Updated 25swift微调的qwen-vl支持吗
Updated 1函数调用会报错
Closedweb demo error
Closed 1inflight_batching
Updated 23Qwen-14B-Chat-Int4运行后预测结果不对
Closed 4qwen-14b int4-awq 量化失败
Closed 7triron部署成功后，每个卡上多出来几个进程
Closed 12Triton部署TensorRT-LLM报错
Closed 9使用autodl编译tensorrt-llm有问题
Closed 6summarize.py运行解答
Closed 1推理加速效果怎么样？
Updated 1Qwen-14B INT4-AWQ 用tp=2时量化失败
Updated 1Triton的显存占用是TensorRT—llm的两倍
Closed 19Qwen-14B-chat 多batch 报错
Closed 3build完之后跑cli_chat.py报错
Closed 15cnn_dailymail
Closed 30qwen-14b-chat-int4转完之后推理乱码
Closed 3多机多卡推理
Updated 3运行build的时候出了点问题
Closed 4