issues
search
InternLM
/
lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
https://lmdeploy.readthedocs.io/en/latest/
Apache License 2.0
3.11k
stars
280
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
使用TurboMind 推理 + Python 代码集成的方式报错
#1835
zhanghanweii
opened
5 days ago
5
[Bug] pytorch方式多卡部署internlm-xcomposer2-vl-7b,报错KeyError: 'parameter name can\'t contain "."'
#1834
zhaoning1987
closed
3 days ago
4
[Feature] How to support do_sample config just like Automodel 能否像Automodel推理中的do_sample参数支持,支持使用确定性生成方法,而不是随机采样
#1833
Leo-yang-1020
opened
6 days ago
5
第一次合并测试
#1832
Nianqitongs
closed
6 days ago
0
[Bug] smoothquant量化Bacihuan2-7B-Chat模型,无法正常量化
#1831
CodexDive
opened
6 days ago
6
[Bug] Qwen-7B-Chat 量化报错 AttributeError: 'RMSNorm' object has no attribute 'variance_epsilon'
#1830
CodexDive
opened
6 days ago
1
Update engine.py to fix small typos
#1829
WANGSSSSSSS
closed
5 days ago
0
Nightly Build for LMDeploy
#1828
zhyncs
opened
6 days ago
4
Model name id returned is weird specially when using Docker [Bug]
#1827
Hugobox
opened
1 week ago
0
[Bug] awq for Qwen2-72B-instruct
#1826
Vincent131499
opened
1 week ago
17
compat internlm2 for pytorch engine
#1825
RunningLeon
closed
5 days ago
4
fix qwen-vl-chat hung
#1824
irexyc
closed
1 week ago
0
drop stop words
#1823
grimoire
opened
1 week ago
7
[Bug] smooth_quant量化后的模型重新运行,lmdeploy无法正常推理
#1822
CodexDive
closed
5 days ago
24
Fix Request completed log
#1821
irexyc
closed
1 week ago
3
Add Jetson platform support (by docker)
#1820
BestAnHongjun
opened
1 week ago
0
[Bug] MiniCPM-llama3-V2_5 启动后使用image url 使用base64 没有回复结果
#1819
weiminw
opened
1 week ago
3
[Bug] Task was destroyed but it is pending! ImageEncoder._forward_loop()
#1818
DefTruth
closed
1 week ago
5
[Feature] Option to also use host memory for the KV cache
#1817
josephrocca
opened
1 week ago
0
int8 kv cache 和 Flash Attention 无法一起使用
#1816
SeibertronSS
closed
1 week ago
2
[Bug] lmdeploy部署intermlm2-chat-20b,遇到<|im_end|>不会停止
#1815
jeinlee1991
opened
1 week ago
5
Add model revision & download_dir to cli
#1814
irexyc
closed
5 days ago
0
[Bug] vl pipeline triggle cudaMemcpyAsync ERROR illegal memory access
#1813
pupumao
opened
1 week ago
10
fix best_match_model
#1812
irexyc
closed
1 week ago
1
check driver mismatch
#1811
grimoire
closed
1 week ago
0
[Bug] 使用领域数据sft qwen2-7b后,转awq 报错
#1810
qiuxuezhe123
opened
1 week ago
0
fix: append _stats when size > 0
#1809
zhyncs
opened
1 week ago
0
支持glm-4-9b吗
#1808
rivhea
opened
1 week ago
2
AsyncEngine create cancel task in exception.
#1807
grimoire
closed
1 week ago
0
fix pr test for newest internlm2 model
#1806
zhulinJulia24
closed
1 week ago
0
[Feature] Please add support for Qwen2
#1805
mihara-bot
closed
4 days ago
2
[Bug] No way to you specify a model revision?
#1804
fake-name
opened
1 week ago
3
[Bug] lmdeploy got nccl error
#1803
linyubupa
closed
1 week ago
4
[Bug] n_token = outputs.num_token . Error: AttributeError: 'tuple' object has no attribute 'num_token'
#1802
Liqiandi
opened
1 week ago
0
[Feature] Prefill/Decoding disaggregation substantially boosts throughput
#1801
serser
opened
1 week ago
9
[Feature] support function calling
#1800
zhyncs
opened
1 week ago
1
feat: auto set awq model_format from hf
#1799
zhyncs
closed
1 week ago
1
PyTorchEngine adapts to the latest internlm2 modeling.
#1798
grimoire
closed
1 week ago
2
Support internvl-chat for pytorch engine
#1797
RunningLeon
closed
5 days ago
3
[Bug] 对Llama-3-70B-Instruct进行量化的时候会出现OOM的问题
#1796
ZGW99
opened
1 week ago
14
[side-effect] fix weight_type caused by PR #1702
#1795
lvhan028
closed
1 week ago
0
[Bug] KeyError: 'Phi3ForCausalLM'
#1794
pseudotensor
opened
1 week ago
6
Support Qwen2-1.5b awq
#1793
AllentDan
closed
4 days ago
5
"Aborted (core dumped)" when running Qwen2-7B-Instruct [Bug]
#1792
kaishxu
closed
1 week ago
7
fix: prevent numpy breakage
#1791
zhyncs
closed
1 week ago
2
[Feature] 多模态api_server推理速度性能测试
#1790
LRHstudy
opened
1 week ago
7
Refine AsyncEngine exception handler
#1789
AllentDan
closed
1 week ago
1
[Bug] Client-aborted streaming requests 'leak', which eventually stalls/crashes turbomind after 100 to 300 requests
#1788
josephrocca
closed
1 week ago
4
是否兼容openai中参数n的设置?尝试设置n>1,但仍然只返回一条结果
#1787
hitsz-zxw
opened
1 week ago
1
[Bug] Qwen/Qwen2-72B-Instruct AWQ Quantization NaN Error
#1786
serser
opened
1 week ago
9
Previous
Next