issues
search
OpenPPL
/
ppl.llm.serving
Apache License 2.0
123
stars
13
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
支持qwen1.5或者qwen2吗?
#64
Flynn-Zh
opened
1 month ago
1
How to generate custom dataset?
#63
trebladev
opened
2 months ago
0
update git deps
#62
syheliel
opened
3 months ago
1
Compilation error
#61
Liu-xiandong
closed
3 months ago
3
关于性能分析的一点疑惑
#60
Zhiy-Zhang
opened
4 months ago
1
[misc] move grpc related to src/serving/grpc
#59
ouonline
closed
4 months ago
0
[fix] fix client of batch response
#58
Vincent-syr
closed
4 months ago
0
fix batch rsp
#57
Vincent-syr
closed
4 months ago
0
compile error:ppl.llm.serving/tools/client_pressure.cc:339:105: error: no matching function for call to ‘std::unique_ptr<grpc::ClientReader<ppl::llm::proto::Response> >::unique_ptr(std::unique_ptr<grpc::ClientReader<ppl::llm::proto::BatchedResponse> >)’
#56
Zhiy-Zhang
closed
4 months ago
4
[feature] sever support token in & out, and batch rsp
#55
Vincent-syr
closed
5 months ago
0
[feature] add early_stopping option
#54
Vincent-syr
closed
5 months ago
0
[feature] add latency distribution for benchmark
#53
Vincent-syr
closed
5 months ago
0
[refactor][doc] add README to internlm and chatglm, refactor model fa…
#52
Alcanderian
closed
7 months ago
0
[feature] support pmx model
#51
xupinjie
closed
7 months ago
0
[fix] fix sampler
#50
Alcanderian
closed
8 months ago
0
[feature] support more cache layout and quant bit=0, quant group=1 for mlu
#49
Vincent-syr
closed
10 months ago
0
Update build.sh
#48
Alcanderian
closed
10 months ago
0
Update build.sh
#47
Alcanderian
closed
10 months ago
0
[fix] fix memory leak error
#46
Vincent-syr
closed
11 months ago
0
[fix] fix compile error with -DPPLNN_CUDA_ENABLE_NCCL=OFF
#45
Vincent-syr
closed
11 months ago
0
Example demo stuck (ppl_llm_server/client_sample)
#44
Kwinpeng
closed
11 months ago
2
[feature] add internlm model support and model, tokenizer factory
#43
Vincent-syr
closed
11 months ago
0
[fix] qps benchmark fix
#42
Vincent-syr
closed
11 months ago
0
[fix][doc] fix worker wait bug, and add llama config explain docs
#41
Vincent-syr
closed
11 months ago
0
[feature] add `quant_method` option
#40
Alcanderian
closed
11 months ago
0
test
#39
Vincent-syr
closed
11 months ago
0
test
#38
ouonline
closed
11 months ago
0
test
#37
Vincent-syr
closed
11 months ago
0
编译出错 [ 17%] Built target crypto as: symbol lookup error: as: undefined symbol: deflate
#36
af-74413592
opened
11 months ago
2
适配 ppl.common 最新的逻辑
#35
Hijdk
closed
11 months ago
3
[fix] fix 13b dead lock error
#34
Vincent-syr
closed
11 months ago
0
[opt] reduce signal count
#33
ouonline
closed
11 months ago
0
[feature] add simple flag, add request rate for benchmark
#32
Vincent-syr
closed
11 months ago
0
[fix] add cache layout mode selecting, sampler deconstruct and misc
#31
Vincent-syr
closed
11 months ago
0
[misc] fix simple error
#30
Vincent-syr
closed
11 months ago
0
serving 运行出错
#29
maiquanshen
closed
10 months ago
2
Syr/dev
#28
Vincent-syr
closed
11 months ago
0
error: 服务器不允许请求未公开的对象 60209eb1ccc34d5deefb002d1b7f37545204f7f2 获取了子模组路径 'third_party/bloaty',但是它没有包含 60209eb1ccc34d5deefb002d1b7f37545204f7f2。直接获取该提交失败。
#27
williamZQ
closed
10 months ago
1
[fix] disable ppl.nn.llm build tools, disable
#26
Alcanderian
closed
12 months ago
0
[fix] server dead lock bug
#25
Vincent-syr
closed
12 months ago
0
[doc] update doc
#24
Alcanderian
closed
12 months ago
0
[refactor][fix] use barrier to fix decoder and work thread sync, refa…
#23
Vincent-syr
closed
12 months ago
0
[feature][refactor] support more tokenizer, optimize stream chat proc…
#22
Vincent-syr
closed
12 months ago
0
Error for llama-13B on V100
#21
yisongsong
opened
12 months ago
3
How to control the request rate in this framework?
#20
LRY89757
closed
12 months ago
3
How to disable kv cache 8-bit quantization?
#19
sleepwalker2017
closed
10 months ago
1
CMakeLists.txt:24 (hpcc_populate_dep) Configuring incomplete, errors occurred!
#18
LMX-xin
closed
10 months ago
2
nccl error
#17
sleepwalker2017
closed
10 months ago
2
support for huggingface llama?
#16
sleepwalker2017
closed
10 months ago
3
[misc] ResourceManager::Init() changes and remove unused funcs
#15
ouonline
closed
12 months ago
0
Next