issues
search
wangzhaode
/
mnn-llm
llm deploy project based mnn.
Apache License 2.0
1.46k
stars
159
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
服务
#173
Vincent131499
closed
5 months ago
7
英伟达T4上使用opencl报错
#172
tzhang2014
closed
5 months ago
3
[Request]: Expose KV Cache Reset functionality.
#171
Nick-infinity
closed
6 months ago
1
请问mnn-llm现在是否支持opencl后端?能否调用GPU?如果希望利用安卓设备的GPU进行推理需要做哪些更改?
#170
qtyandhasee
closed
7 months ago
5
Error: No encoding found for the sequence starting at position 0
#169
OliverQueen1466
closed
7 months ago
5
Error for concat size of op [ /block/self_attn/Concat_5_output_0 ], the 1 input not match output
#168
yysu-888
closed
5 months ago
3
TinyLlama-1.1B 能正常运行,但是“胡说八道”
#167
BUG1989
closed
6 months ago
2
Ubuntu20.04 x86-64,TinyLlama Segmentation fault
#166
BUG1989
closed
7 months ago
2
iOS demo cannot work ,becasue of memory limit
#165
Fengur
closed
6 months ago
1
Build failure on Linux: missing headers in tokenizer.cpp
#164
skmkt
closed
7 months ago
1
在linux的cpu下测试的效率对不上
#163
tzhang2014
closed
7 months ago
1
编译MNN需要有什么改动
#162
MuYu-zhi
closed
7 months ago
1
google gemma 也开源了
#161
kekxv
closed
7 months ago
1
增加對qwen1.5 1.8b的支持
#160
CRGBS
closed
7 months ago
3
修正README文本错误
#159
FiveHair
closed
8 months ago
0
Segmentation Fault in PC Linux
#158
iamfaith
closed
7 months ago
2
iOS demo 内存泄漏
#157
LionWY
closed
7 months ago
1
下载完qwen-1.8b-mnn-int8,加载完还是无法到聊天页面
#156
do-one-thing-to-well
closed
7 months ago
4
求分享多模态模型的示例和性能数据
#155
XiaotaoChen
closed
9 months ago
1
求大佬修复这个DISK_EMBEDDING需要`embeddings_bf16.bin` 文件问题!
#154
do-one-thing-to-well
closed
9 months ago
3
为什么同样是4bit量化模型,mnn-llm会比llama.cpp快几倍呢?
#153
22dimensions
closed
9 months ago
1
Please upgrade your GNU compiler to one that supports __declspec
#152
do-one-thing-to-well
closed
9 months ago
11
在Windows下无法下载Qwen-1_8B-Chat-int8 模型
#151
do-one-thing-to-well
closed
9 months ago
2
有什么途径可提高输出质量?(Phi2 参考)
#150
kmn1024
closed
9 months ago
4
<fix>: enable int4 inference for llm >= 6b, or load model will fail.
#149
waterdropw
closed
9 months ago
0
fix compilation error on Android
#148
windmaple
closed
9 months ago
0
自己编译的apk运行速度很慢
#147
litao1991
closed
8 months ago
4
Llama2-7B模型在MNN-LLM框架下的性能明显优于MLC-LLM吗
#146
ZW-BOY1126
closed
8 months ago
3
手机加载完Phi2模型后,聊天界面提问会出现闪退到加载模型界面。
#145
ZW-BOY1126
closed
8 months ago
1
[Regression]: Unable to reproduce Inference performance of qwen 1.8B int4 model.
#144
Nick-infinity
closed
9 months ago
0
下载llama2-7B模型后,将其push到手机上,可以显示模型文件夹,但是无法到聊天界面
#143
ZW-BOY1126
closed
8 months ago
3
关于Qwen-VL 的支持
#142
JennieGao-njust
closed
8 months ago
1
fix block_num value in model download script
#141
xiaoqiang306
closed
9 months ago
0
[Question]: Add support for tinyllama 1.1 B model
#140
Nick-infinity
closed
9 months ago
1
qwen-1.8 转换的mnn和官网提供的mnn block文件大小不一样,我转的mnn最终是39m 官方的是24.6M
#139
moyu505
closed
9 months ago
3
HELP! 安卓端版mnn-llm.apk加载chatglm3-6b-mnn无法操作
#138
forhonourlx
closed
8 months ago
5
能否发挥 NPUs of 天玑9300 或者 骁龙 8gen3?
#137
forhonourlx
closed
9 months ago
6
Plans for android GPU suppport for qwen 1.8B
#136
Nick-infinity
closed
8 months ago
7
qwen-1.8b-apk 使用时程序崩溃
#135
MeetUo
closed
8 months ago
6
Android Studio加载模型问题
#134
0three
closed
10 months ago
10
fix: readme errors
#133
M1saka10010
closed
10 months ago
0
Android studio运行adb shell "cd /data/local/tmp && export LD_LIBRARY_PATH=. && ./cli_demo -m model"时报错如下
#132
0three
closed
10 months ago
2
Kernel MNNGemmHybridInt4 will cause segmentation fault in ARM devices
#131
Lqlsoftware
closed
10 months ago
2
不能正常输出
#130
wanshichenguang
closed
10 months ago
1
VARP Llm::disk_embedding疑问
#129
Moxoo
closed
10 months ago
5
chatglm2-6b-mnn 第二次推理coredump
#128
Moxoo
closed
10 months ago
7
细节优化
#127
kekxv
closed
10 months ago
0
关于llm中is_single的含义,是否进行了模型拆分从而获得多线程加速
#126
Liu-xiandong
closed
10 months ago
3
android+opencl编译报错
#125
sunzhe09
closed
11 months ago
5
完全不能用,Android工程都跑不起来,脚本几乎每一步都有错误。用这个库简直恶心啊。
#124
Pangu-Immortal
closed
11 months ago
2
Previous
Next