Giters
MegEngine
/
InferLLM
a lightweight LLM model inference framework
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
666
Watchers:
10
Issues:
54
Forks:
81
MegEngine/InferLLM Issues
有打算支持qwen吗
Updated
2 months ago
在树莓派3b+上部署,出现无法打开模型的问题
Updated
2 months ago
Comments count
4
How to build wasm file?
Closed
3 months ago
这个有windows的部署教程吗
Updated
4 months ago
在运行llama2-13b的时候出现以下问题
Updated
5 months ago
Linux 运行时报以下错误
Closed
a year ago
Comments count
12
移植问题
Updated
7 months ago
请问可以在不支持V扩展的RISC-V CPU上运行吗
Updated
7 months ago
Comments count
1
arm 平台输出乱码
Updated
7 months ago
Comments count
3
可以在RV64指令集的CPU上运行吗
Closed
8 months ago
I got the error on centos 7: failed to tokenize string!
Updated
8 months ago
Comments count
2
make报错
Updated
8 months ago
Comments count
3
chatglm3有计划支持吗?
Updated
9 months ago
Comments count
3
感觉回答有些错乱,用的是macbook pro 推理chinese-alpaca-7b-q4
Updated
9 months ago
Comments count
5
mac os Big Sur 11.7.4 Linking Error , Undefined symbols
Closed
9 months ago
Comments count
1
请问是否有计划支持Whisper?
Closed
10 months ago
Comments count
1
ChatGLM2 效果异常
Closed
10 months ago
Comments count
1
unsupported relocation 37 on musl libc
Closed
a year ago
Comments count
3
chatglm2 GPU版本的int4、int8量化模型预测结果异常
Closed
a year ago
Comments count
1
能否改为GPU辅助计算
Updated
a year ago
Comments count
6
windows下面编译失败
Updated
a year ago
Comments count
8
Thread wakening may be bottom neck for large core systems
Updated
a year ago
Comments count
8
【new feature】通义千问有没有计划支持
Updated
a year ago
Comments count
2
请问一下,这个是不是比python的性能更好?
Updated
a year ago
Comments count
1
大模型推理中这个推理引擎如何支持 lora,ptuning等私有语料训练插件后的新模型
Updated
a year ago
Comments count
2
make error
Updated
a year ago
Comments count
13
O3 optimization are slower on SG2042
Updated
a year ago
Comments count
3
Please support RWKV for refs and compare.
Updated
a year ago
目前不支持gpu跑吗?我看代码中有添加对gpu的支持啊
Updated
a year ago
Comments count
2
请问主循环中的token指代的是什么呢?函数体内部也没有看出来是代表什么
Updated
a year ago
Comments count
1
ChatGLM 2已经出了,什么时候可以支持一下啊
Updated
a year ago
Comments count
10
编译错误,需要添加 -mfma 才能编译通过,但是 CPU 指令集不支持 fma,导致运行出错。
Closed
a year ago
Comments count
5
chatglm-6b下的模型格式不正确
Closed
a year ago
Comments count
1
Compile error: void inferllm::BaiChuanGraph::constuct_llm()? marked ?override?, but does not override
Closed
a year ago
Comments count
4
希望可以封装openai兼容API
Updated
a year ago
【feature】baichuan-7b模型能不能使用baichuan-vicuna-chinese-7b模型文件
Updated
a year ago
没有支持最新的llama.cpp的格式吗
Updated
a year ago
asserts 那个目录,建议改成 assets
Closed
a year ago
Comments count
1
在线程数>1时,会占满cpu核心
Updated
a year ago
Comments count
3
decode & decode_iter 多线程会不会有问题
Updated
a year ago
向量计算中使用CPU AVX指令,能否支持不使用AVX指令的版本
Updated
a year ago
Comments count
1
请问如何实现的量化?
Closed
a year ago
Comments count
2
更新的太慢了,求加速
Updated
a year ago
Comments count
2
是否有计划优化GPU上的推理加速
Updated
a year ago
Comments count
3
isnan报错
Updated
a year ago
Comments count
1
Support input prompt like llama.cpp
Updated
a year ago
有实现思维树方式么
Updated
a year ago
tokenizer 在哪里下载
Closed
a year ago
Comments count
2
希望能编译成so文件
Closed
a year ago
Comments count
3
超参的理解是否是正确的?
Updated
a year ago
Comments count
2
Previous
Next