issues
search
li-plus
/
chatglm.cpp
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
MIT License
2.92k
stars
333
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
能支持arm64架构的linux环境编译吗
#348
QDPeng
opened
2 weeks ago
0
ggml_gallocr_needs_realloc: node node_24 is not valid
#347
shampoo6
closed
2 weeks ago
2
你好,我的开发环境有2张卡,推理时想使用2张卡进行并行推理。请问推理时,可以指定用哪张卡吗
#346
XiaoYangWu
opened
3 weeks ago
0
glm-4-9b-chat量化bin模型(精度q8_0)调用function calling失败
#345
rustjiao
opened
3 weeks ago
0
使用量化模型出现错误
#344
XiaoQiu2451
closed
1 month ago
1
关于在Windows环境下编译CUDA版本出现的问题和一些应该去标明环境的细节
#343
XiaoQiu2451
opened
1 month ago
1
运行./build/bin/main -m models/chatglm-ggml.bin -p 你好时报错, '.' 不是内部或外部命令,也不是可运行的程序 或批处理文件。
#342
yuanyuanwang123
opened
1 month ago
2
CUDA可用,但是推理时还是用的CPU
#341
sxsp
opened
1 month ago
0
能兼容aarch64架构的cpu吗
#340
dailinyucode
closed
1 month ago
3
Apply flash attention on vision encoder
#339
li-plus
closed
2 months ago
0
跑比较长文本推理报错
#338
leizhu1989
opened
2 months ago
4
Fix compilation on metal
#337
li-plus
closed
2 months ago
0
Support GLM4V
#336
li-plus
closed
2 months ago
0
支持glm4v多模态模型
#335
liyuan1208
closed
2 months ago
0
Python脚本 加载转化模型非常慢
#334
qiuwenbo1
closed
2 months ago
1
推理输入不同文字长度有时会出现 check failed (std::isfinite(next_token_logits[i])) nan/inf encountered at lm_logits[0]
#333
leizhu1989
closed
2 months ago
3
有关内容总结质量
#332
leizhu1989
opened
3 months ago
0
量化模型再T4服务器不能调用GPU资源,是什么原因呢?
#331
hithepeng
opened
3 months ago
1
并发问题
#330
Ab-123
opened
3 months ago
1
mac m1 pro 16G运行glm4-ggml报错
#329
lwo2002
opened
3 months ago
1
self.tokenizer is none, how to solve this problem.
#328
lzj-r
opened
3 months ago
3
can not import chatglm_cpp, add the following code to the web-demo.py
#327
lzj-r
opened
3 months ago
0
请问是否支持glm-4-9b-chat-1m模型量化
#326
leizhu1989
opened
3 months ago
3
在ARM上构建docker镜像出现异常
#325
hooploop
opened
3 months ago
0
hf上下载的gguf量化后的模型文件,运行报错
#324
vaxilicaihouxian
closed
3 months ago
1
问题:python安装v0.4.0导致卡死,有没有能控制编译资源的选项?
#323
ChengjieLi28
opened
3 months ago
0
Fix nan by rescheduling attention scaling
#322
li-plus
closed
3 months ago
0
在maos上启用metal的话似乎必须安装xcode了?
#321
mahabuta
opened
3 months ago
1
同一模型,open_api.py的显存用量显著大于cli
#320
3wweiweiwu
closed
3 months ago
1
openai server出现空回答
#319
FuturePrayer
closed
3 months ago
2
glm4量化之后开始胡言乱语有人遇到过吗?
#318
piaodangdang
opened
3 months ago
7
Disable shared library by default. Set default max_length in api server.
#317
li-plus
closed
3 months ago
0
libre2.so.11 not found
#316
hooploop
closed
3 months ago
1
chatglm_cpp-0.3.4 终于成功了
#315
sqhua
opened
3 months ago
0
Fix regex lookahead for code input tokenization
#314
li-plus
closed
3 months ago
0
使用openai_api.py启动量化后的glm4模型报错
#313
gabrielpondc
closed
3 months ago
4
请问是否支持了GLM-4V?
#312
yhl41001
closed
2 months ago
7
openai server非流式请求报错
#311
FuturePrayer
closed
3 months ago
6
glm4运行报错
#310
zArche
closed
3 months ago
1
Use apply_chat_template to calculate tokens
#309
dixyes
closed
3 months ago
1
Can't use web_demo in glm4
#308
jtc1246
closed
3 months ago
1
chatglm4: Run ./build/bin/main, Error: invalid model type 4
#307
guissy
closed
3 months ago
2
Update py interface
#306
li-plus
closed
3 months ago
0
Dynamic memory allocation. Drop Baichuan/InternLM support in favor of llama.cpp.
#305
li-plus
closed
3 months ago
0
Add ChatGLM model type & tokenizer to pybind
#304
li-plus
closed
3 months ago
0
Support ChatGLM4 conversation mode
#303
li-plus
closed
3 months ago
1
Will it support glm-4-9b-chat?
#302
okwinds
closed
3 months ago
1
GLM-4-9B已发布,是否有支持计划
#301
yuezhishun
closed
3 months ago
12
build之后,缺少main文件
#300
wwwsctvcom
opened
4 months ago
0
win11 chatglm3-6b 转换 q4_0报错
#299
S0uLHun43r
closed
4 months ago
0
Next