issues
search
QwenLM
/
qwen.cpp
C++ implementation of Qwen-LM
Other
506
stars
39
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
qwen2 support
#82
bil-ash
opened
3 weeks ago
1
[BUG] 多轮对话的 prompt 应该如何构建?
#81
791136190
opened
1 month ago
0
qwen1.5 support?
#80
anan1213095357
opened
4 months ago
2
使用qwen.cpp对原模型进行转化为什么文件反而增大了?
#79
zzzcccxx
opened
4 months ago
0
Does it support Qwen1.5 Model?
#78
kicGit
opened
4 months ago
8
Python Binding之后,如何只使用cpu进行推理呢?
#77
zzzcccxx
closed
4 months ago
0
why missing "assistant" here
#76
feixyz10
opened
5 months ago
0
crash if compliing in debug mode, everything is ok if in release mode
#75
feixyz10
opened
5 months ago
0
如何下载tiktoken_cpp
#74
eswulei
opened
5 months ago
0
添加tokens生成速度
#73
OliverQueen1466
opened
5 months ago
0
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
#72
suyu-zhang
opened
5 months ago
0
Why does `TextStreamer` hold on punctuation?
#71
Wovchena
opened
5 months ago
0
windows 下使用qwen.cpp 问题
#70
kingpingyue
opened
6 months ago
0
[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?
#69
Lyzin
opened
6 months ago
4
add readme for Chinese
#68
litongjava
opened
6 months ago
1
多轮会话
#67
litongjava
opened
6 months ago
0
如何将gradio架构构建的前端和qwen-cpp推理代码连接?
#66
tougeqaq
opened
6 months ago
2
💡 [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
#62
micronetboy
opened
6 months ago
0
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
#61
micronetboy
opened
6 months ago
0
希望团队能继续支持qwen.cpp
#60
awtestergit
opened
6 months ago
3
💡 [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
#63
micronetboy
opened
6 months ago
0
💡 [Question] - QwenCPP Python Binding 如何 支持 BLAS CPU 加速
#64
micronetboy
opened
6 months ago
2
Python Binding 如何 支持BLAS CPU 加速
#59
micronetboy
opened
6 months ago
0
pip install -U qwen-cpp 报错
#58
micronetboy
opened
6 months ago
3
fix: Fixing static compilation issues when installing modules with pip
#57
uniartisan
opened
6 months ago
0
💡 [REQUEST] - CPU 的 qwen-cpp 如何封装为一个 http 服务?
#65
micronetboy
opened
6 months ago
4
为啥qwen.cpp在A100和A10性能差距很大
#56
zhangzai666
opened
6 months ago
1
CUDA error 2 at /home/qwen.cpp/third_party/ggml/src/ggml-cuda.cu:7196: out of memory
#55
youngallien
opened
7 months ago
0
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。
#54
bigbigtooth
opened
7 months ago
1
qwen_cpp可以提供api接口实现web服务么
#53
zhangzai666
opened
7 months ago
1
python-bind报错 ERROR: Could not build wheels for qwen-cpp, which is required to install pyproject.toml-based projects
#52
zhangzai666
opened
7 months ago
2
请问7b的模型量化需要多大的内存,我这一直显示out of memory
#51
WCSY-YG
opened
7 months ago
0
qwen.cpp合并到llama.cpp中之后,对于<|im_start|>、<|im_end|>似乎没有正确处理
#50
listeng
opened
7 months ago
0
代码ctx_w_size
#49
EveningLin
opened
7 months ago
0
Update README.md
#48
simonJJJ
closed
7 months ago
0
72B模型量化需要多大内存,192G的内存都会被kill掉
#47
sweetcard
opened
7 months ago
9
Support for AMD‘s ROCm
#46
riverzhou
opened
7 months ago
5
Support `--gpu-layers`
#45
lindeer
closed
6 months ago
7
GGML_ASSERT when using a long prompt
#44
Ayahuasec
opened
7 months ago
2
python binding无法正常安装
#43
passionate11
opened
7 months ago
2
Qwen-7B-Q4_0 works well on Mac M1, but Qwen-7B-Q8_0 cannot work with a ggml-metal error.
#42
songkq
opened
7 months ago
1
feat: add more max_length constraint for resource limit machines
#41
fann1993814
opened
7 months ago
0
Update tiktoken.h
#40
xiyihan0
opened
7 months ago
0
feat: add metal support
#39
fann1993814
closed
7 months ago
0
Does the Owen.cpp support macOS metal build?
#38
AndreaChiChengdu
opened
8 months ago
1
Python Binding在windows下无法编译
#37
AppleJunJiang
opened
8 months ago
1
很容易出现 UnicodeDecodeError: 'utf-8' codec can't decode bytes
#36
zhcharles
opened
8 months ago
6
Create openai_api.py
#35
yuebo
opened
8 months ago
0
'QWenConfig' object has no attribute 'intermediate_size'
#34
dingli06
opened
8 months ago
0
Python Binding 报错
#33
xinbingzhe
opened
8 months ago
3
Next