Giters
QwenLM
/
qwen.cpp
C++ implementation of Qwen-LM
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
536
Watchers:
9
Issues:
74
Forks:
47
QwenLM/qwen.cpp Issues
如何在x86架构上进行交叉编译到ARM64架构?
Updated
20 days ago
[BUG] Qwen-1.8-Chat,用llama.cpp量化为f16,然后推理回答错乱,请问1.8在llama.cpp还不支持吗?
Updated
24 days ago
Comments count
5
对qwen1.5模型进行lora微调,怎么加载微调的参数,怎么将微调后的模型进行转换
Closed
a month ago
'QWenConfig' object has no attribute 'intermediate_size'
Updated
a month ago
Comments count
1
qwen2 support
Updated
3 months ago
Comments count
1
[BUG] 多轮对话的 prompt 应该如何构建?
Updated
4 months ago
pip install -U qwen-cpp 报错
Updated
5 months ago
Comments count
3
qwen1.5 support?
Updated
6 months ago
Comments count
2
如何将gradio架构构建的前端和qwen-cpp推理代码连接?
Updated
6 months ago
Comments count
2
Does it support Qwen1.5 Model?
Updated
7 months ago
Comments count
8
使用qwen.cpp对原模型进行转化为什么文件反而增大了?
Updated
7 months ago
Python Binding之后,如何只使用cpu进行推理呢?
Closed
7 months ago
Support `--gpu-layers`
Closed
9 months ago
Comments count
7
Python Binding 报错
Updated
8 months ago
Comments count
3
python binding无法正常安装
Updated
8 months ago
Comments count
2
在MacOS,用python调用qwen_cpp载入模型进行推理,只能启动CPU,无法使用GPU。
Updated
8 months ago
Comments count
1
python-bind报错 ERROR: Could not build wheels for qwen-cpp, which is required to install pyproject.toml-based projects
Updated
8 months ago
Comments count
2
qwen_cpp可以提供api接口实现web服务么
Updated
8 months ago
Comments count
1
Qwen-7B-Chat WSL GPU Error: ankerl::unordered_dense::map::at(): key not found
Updated
8 months ago
Comments count
2
why missing "assistant" here
Updated
8 months ago
crash if compliing in debug mode, everything is ok if in release mode
Updated
8 months ago
如何下载tiktoken_cpp
Updated
8 months ago
添加tokens生成速度
Updated
8 months ago
请问用qwen.cpp量化后的模型如何使用optimum-benchmark进行性能基准测试,现在参照readme中所述只得到一个build文件夹,不清楚如何进行下一步的测试
Updated
8 months ago
Why does `TextStreamer` hold on punctuation?
Updated
9 months ago
windows 下使用qwen.cpp 问题
Updated
9 months ago
希望团队能继续支持qwen.cpp
Updated
9 months ago
Comments count
3
多轮会话
Updated
9 months ago
💡 [REQUEST] - CPU 的 qwen-cpp 如何封装为一个 http 服务?
Updated
9 months ago
Comments count
4
💡 [Question] - QwenCPP Python Binding 如何 支持 BLAS CPU 加速
Updated
9 months ago
Comments count
2
💡 [Question] - <title>qwen-cpp 只使用 cpu 和 启用 cpu BLAS 加速, 在都不使用GPU的情况下,速度有多大差别?我测试没有差别
Updated
9 months ago
💡 [Question] - 您好,请教个问题,qwen-cpp BaseStreamer 如何通过std::string 构造一个 BaseStreamer?C++代码少一个构造方式
Updated
9 months ago
您好,请教个问题,qwen-cpp BaseStreamer 如何通过std::string 构造一个 BaseStreamer?C++代码少一个构造方式
Updated
9 months ago
为啥qwen.cpp在A100和A10性能差距很大
Updated
9 months ago
Comments count
1
Python Binding 如何 支持BLAS CPU 加速
Updated
9 months ago
Python Binding在windows下无法编译
Updated
10 months ago
Comments count
1
CUDA error 2 at /home/qwen.cpp/third_party/ggml/src/ggml-cuda.cu:7196: out of memory
Updated
10 months ago
72B模型量化需要多大内存,192G的内存都会被kill掉
Updated
10 months ago
Comments count
9
请问7b的模型量化需要多大的内存,我这一直显示out of memory
Updated
10 months ago
qwen.cpp合并到llama.cpp中之后,对于<|im_start|>、<|im_end|>似乎没有正确处理
Updated
10 months ago
代码ctx_w_size
Updated
10 months ago
Support for AMD‘s ROCm
Updated
10 months ago
Comments count
5
很容易出现 UnicodeDecodeError: 'utf-8' codec can't decode bytes
Updated
10 months ago
Comments count
6
GGML_ASSERT when using a long prompt
Updated
10 months ago
Comments count
2
Qwen-7B-Q4_0 works well on Mac M1, but Qwen-7B-Q8_0 cannot work with a ggml-metal error.
Updated
10 months ago
Comments count
1
Does the Owen.cpp support macOS metal build?
Updated
a year ago
Comments count
1
64位linux系统pip安装qwen_cpp报错,不支持?
Updated
a year ago
pip 安装 qwen-cpp 需要X86-32位的系统吗?能否支持X86-64位的系统
Updated
a year ago
Inferential capability of qwen.cpp for Qwen-14b-chat is different compared with Qwen-14b-chat of CUDA
Updated
a year ago
Can you add an additional function to let convert.py support Qwen/Qwen-7B-Chat-Int4?
Updated
a year ago
Previous
Next