thunlp/InfLLM Issues
可以与vllm集成吗？
Updated关于longbench测试问题。
Closed 1longbench
Closed是否支持多batch推理？
Closed 5实际测试效果较差
Updated 4是否支持Qwen1.5-7B的量化版本？
Closed 11Needle In A Haystack test?
Updated 1How to use w transformers?
Updated 4Code licence
Closed 2多卡支持问题
Closed 2是否可以添加faiss向量库的保存和加载
Closed 1代码实现的疑问
Closed 3OOM issue
Closed 1Qwen1.5-7B-Chat
Closed 10cuda error
Closed 7我看代码会不定期更新，做了什么改动可以加到readme里吗
Closed 1Qwen1.5-72B-Chat-GPTQ-Int4
Closed 2能否将所有的kv缓存存到faiss向量数据库里
Closed 12内存占用会不会很大
Closed 3GPU memory usage at benchmark
Closed 3显存占用问题
Closed 1Request for parameter comment
Closed 1能否支持多卡推理
Closed 1More generate parameters
Closed 1推理时间问题
Closed 2qwen系列模型支持
Closed 6准确率问题
Closed 1长文本报错
Closed 1