issues
search
InternLM
/
lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
https://lmdeploy.readthedocs.io/en/latest/
Apache License 2.0
3.13k
stars
280
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
[Bug]
#1894
CodexDive
opened
5 hours ago
2
GenerationConfig 类中的参数n没有发挥作用
#1893
1452083640
opened
6 hours ago
3
docs: update cache-max-entry-count help message
#1892
zhyncs
closed
7 hours ago
4
单条样本推理可以不使用stream_infer吗
#1891
zhanghanweii
opened
8 hours ago
4
Fix internlm-xcomposer2-vl awq search scale
#1890
AllentDan
closed
5 hours ago
0
feat: support llama2 and internlm2 on 910B
#1889
yao-fengchen
opened
9 hours ago
1
need gemma2 support
#1888
zzc0208
closed
10 hours ago
1
[Doc]: Update docs for internlm2.5
#1887
RunningLeon
closed
8 hours ago
1
fix qwen2 cache_position for PyTorch Engine when transformers>4.41.2
#1886
zhyncs
closed
10 hours ago
5
[Bug] qwen 2 issue when transformers>4.41.2 for PyTorch Engine
#1885
zhyncs
closed
10 hours ago
4
[Feature] blazing great work about KV Cache: Mooncake
#1884
zhyncs
opened
2 days ago
4
[Bug] 量化时候采取默认参数能够正常推理量化,设置了--search-scale True --batch-size 8,量化后无法推理
#1883
AIFFFENG
closed
2 hours ago
6
[Feature] Function call
#1882
PredyDaddy
closed
3 days ago
1
Fix error link reference
#1881
zihaomu
closed
6 hours ago
2
[Doc]: Change to sphinx-book-theme in readthedocs
#1880
RunningLeon
opened
3 days ago
0
[Feature] long context inference optimization
#1879
zhyncs
opened
3 days ago
2
[Feature] support Gemma 2
#1878
zhyncs
opened
3 days ago
2
docs: update faq for turbomind so not found
#1877
zhyncs
opened
3 days ago
0
Add usage in stream response
#1876
fbzhong
opened
3 days ago
2
misc: rm unnecessary files
#1875
zhyncs
closed
6 hours ago
0
fix SamplingDecodeTest and SamplingDecodeTest2 unittest failure
#1874
zhyncs
closed
4 hours ago
4
fix gradio vl "stop_words"
#1873
irexyc
closed
4 days ago
2
[Docs] TurboMind推理引擎与PyTorch推理引擎速度对比
#1872
LRHstudy
opened
4 days ago
1
[Bug] 不支持qwen0.5b的加速?以及qwen0.5b的awq量化?
#1870
qism
opened
4 days ago
5
[Bug] InternVL 1.5性能瓶颈在ViT,有计划支持ViT TM backend+TP推理不?
#1869
DefTruth
closed
3 days ago
2
[Bug] AttributeError: 'LlavaNextConfig' object has no attribute 'hidden_size'
#1868
zhaozeno
opened
4 days ago
2
fix model name matching for internvl
#1867
RunningLeon
closed
4 days ago
0
[Bug] internvl 模型被推理后,针对图片内容回答的答案不正确
#1866
seven1122
opened
4 days ago
6
How to quantify deepseek-ai/deepseek-vl-7b-chat
#1865
SunnyLee20230523
closed
4 days ago
4
使用pipeline加载Qwen1.5-32B-Chat,tp=4,使用openai prompt格式提示其清洗中文但生成回复都是英文
#1864
Yang-bug-star
opened
5 days ago
0
使用OpenAI format的输入得到的response要如何提取出回复文本,返回的response好像是分段的
#1863
Yang-bug-star
opened
5 days ago
2
[Bug] 单轮的图文交错对话的实现原理
#1862
stay-leave
opened
5 days ago
1
react test evaluation config
#1861
zhulinJulia24
closed
5 days ago
0
Fix vl session-len
#1860
AllentDan
closed
5 days ago
1
[side-effect] bring back "--cap" argument in chat cli
#1859
lvhan028
closed
5 days ago
1
misc: update torch version range to 2.3.0
#1858
zhyncs
closed
8 hours ago
1
[Feature] update the range of torch versions
#1857
zhyncs
closed
8 hours ago
4
Support guided decoding for pytorch backend
#1856
AllentDan
opened
5 days ago
0
feat: decouple input_ids and output_ids
#1855
zhyncs
opened
5 days ago
1
vision model use tp number of gpu
#1854
irexyc
opened
5 days ago
1
Optimize sampling on pytorch engine.
#1853
grimoire
opened
6 days ago
0
bump version to v0.5.0
#1852
lvhan028
closed
7 hours ago
5
[Bug] python -m lmdeploy.serve.proxy.proxy --server_name "xxx" --server_port xxx --strategy "min_expected_latency"
#1851
zeroneway
closed
5 days ago
1
misc: align PyTorch Engine temprature with TurboMind
#1850
zhyncs
closed
5 days ago
1
[Bug] Segmentation fault: address not mapped to object at address 0x2058
#1849
austingg
opened
6 days ago
4
under stream mode, if break generator in advance, it may lead to server stuck [Bug]
#1848
shanekong
closed
5 days ago
3
[Bug] InternLM2MLP.forward() missing 1 required positional argument: 'im_mask'
#1847
jiangjingz
opened
6 days ago
2
如何指定模型的数据类型为f16
#1846
Yang-bug-star
opened
6 days ago
1
Support phi3-vision
#1845
RunningLeon
opened
6 days ago
0
Maybe a workaround for qwen2 quantization Nan error
#1844
AllentDan
opened
6 days ago
3
Next