InternLM/lmdeploy

View on GitHub

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Stars: 8.1k
Forks: 751
Open beginner issues: 0
Indexed issues: 546
Avg merge: 6d 2h
Merged PRs (30d): 54

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 18, 2026
Latest indexed: Sep 17, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Open All

546 open issues indexed

多lora Open

InternLM/lmdeploy#3981 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Bug] InternVL3-8B Quantization Open

InternLM/lmdeploy#3988 · 2 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
[Bug] InternVL3_5-8B failed with out of resource: shared memory, Required when tp=2 Open

InternLM/lmdeploy#3992 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] InternVL3_5-8B stuck during starting up with tp=2 Open

InternLM/lmdeploy#3993 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] PyTorchEngine 性能分析没有保存文件 Open

InternLM/lmdeploy#3996 · 4 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Feature] DeepConf Support Open

InternLM/lmdeploy#4007 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Docs] 支持量化压缩Intern-S1 和InternVL3_5-241B-A28B 吗? Open

InternLM/lmdeploy#4009 · 2 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
[Feature] 使用lmdeploy里的pipeline推理可以关掉qwen3的推理模式吗 Open

InternLM/lmdeploy#4010 · 9 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Bug] AMD显卡运行出现错误 Open

InternLM/lmdeploy#4022 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Bug] 多模型下输入图片提示没有ResizeD等操作，无法使用多模态，只能纯文本推理 Open

InternLM/lmdeploy#4038 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] 使用v0.10.1版本部署internvl2.5-38b-mpo-awq报错，如何解决？ Open

InternLM/lmdeploy#4040 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Feature] 请求支持GLM-4.6 Open

InternLM/lmdeploy#4045 · 0 comments · 3 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug]version 0.10.1 : gpt-oss-20b and gpt-oss-120b model returns null message.content on API server Open

InternLM/lmdeploy#4049 · 3 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
[Feature] 请求支持MiniCPM-V 4.5 Open

InternLM/lmdeploy#4050 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Bug] 沐曦C500推理报错 Open

InternLM/lmdeploy#4051 · 3 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] SDAR模型推理 Open

InternLM/lmdeploy#4052 · 3 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] 使用LMdeploy在v100推理 Qwen2.5-VL-32B 过一段时间就会卡住 Open

InternLM/lmdeploy#4053 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Feature] lmdeploy支持多卡量化吗？ Open

InternLM/lmdeploy#4059 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
是否支持多模态的多lora推理 Open

InternLM/lmdeploy#4067 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Feature] 请求支持qwen3-VL和deepseekOCR Open

InternLM/lmdeploy#4072 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Feature] Can we support parameter n in OpenAI compatible API? Open

InternLM/lmdeploy#4073 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Feature] Ernie4.5支持 Open

InternLM/lmdeploy#4085 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
[Bug] Qwen2.5-72B-Instruct-AWQ识图就报错 Open

InternLM/lmdeploy#4113 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Bug] 多模态模型pytorch后端TTFT时间比tubomind后端TTFT时间要长很多 Open

InternLM/lmdeploy#4114 · 0 comments · 1 reaction · 1 assignee · Indexed Sep 17, 2026
[Feature] 请求支持MolmoAct Open

InternLM/lmdeploy#4115 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Feature] Qwen3-VL turbomind support Open

InternLM/lmdeploy#4122 · 9 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] qwen3-vl 在线服务启动报错 Error code: 400 - {'message': 'Logprobs or top_logprobs requested but not enabled logprobs_mode in engine configuration.', 'type': 'invalid_request_error', 'code': 400, 'param': None, 'object': 'error'} Open

InternLM/lmdeploy#4123 · 4 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
hunyuan模型求支持！除了修改源码还有其他方法支持混元模型吗？ Open

InternLM/lmdeploy#4129 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
在沐曦C500上部署InternVL2.5-26B模型失败 Open

InternLM/lmdeploy#4131 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Feature] Aarch64 Support Open

InternLM/lmdeploy#4146 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Bug] Does LMDeploy currently support loading LoRA adapters (single or multiple) for InternVL3 and Qwen2.5-VL models? Open

InternLM/lmdeploy#4162 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] 如何在910B4 A2 NPU 显卡上基于lmdeploy 部署 INTERNVL-38B, 量化模型,尝试很多方式，都是失败告终 Open

InternLM/lmdeploy#4169 · 9 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Feature] 使用v0.10.2版本和vllmv0.10.2镜像部署Llama2-7b|13B,tp=1对比差距很大,是应为是啥原因 Open

InternLM/lmdeploy#4174 · 6 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] crash when sleep but not wakeup in version 0.11.0 Open

InternLM/lmdeploy#4182 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] torbomind和pytorch 推理qwen2.5 vl 7b 差距较大？ Open

InternLM/lmdeploy#4195 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Feature] 请求在 TurboMind 引擎中实现 InternVL3 和 Qwen2.5VL 的前缀缓存 (Prefix Caching) 功能 Open

InternLM/lmdeploy#4205 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
[Bug] SDAR模型logprob Open

InternLM/lmdeploy#4206 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] lmdeploy_dlinfer/ascend API Server流式输出问题 Open

InternLM/lmdeploy#4209 · 3 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Feature] LLaDA 2.0 support Open

InternLM/lmdeploy#4211 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Feature] made api_server model-name case insensitive in request Open

InternLM/lmdeploy#4225 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
8*5060ti performance is low Open

InternLM/lmdeploy#4226 · 18 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Feature] qwen3vl量化 Open

InternLM/lmdeploy#4239 · 3 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] double free or corruption (fasttop) Open

InternLM/lmdeploy#4266 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Feature] Support for RLM via REPL Open

InternLM/lmdeploy#4279 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[Bug] 昇腾310p部署InternVL3-8B，涉及图片回答报错No supported Ops kernel and engine are found for [ResizeD154], optype [ResizeD]. Open

InternLM/lmdeploy#4284 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Feature] 请求支持qwen3-coder-next Open

InternLM/lmdeploy#4327 · 3 comments · 5 reactions · 0 assignees · Indexed Sep 17, 2026
GLM-4.7-FLASH和Qwen3-Coder-Next都不支持 Open

InternLM/lmdeploy#4335 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
cannot run glm4.7-flash on 4*32GB V100 Open

InternLM/lmdeploy#4367 · 21 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Bug] 96G显存RTX6000显卡/windows系统/用turbomind推理引擎运行Qwen3-30B-A3B-AWQ模型，报错，显存超出 Open

InternLM/lmdeploy#4401 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[Feature] 请求支持Intern-S1和Intern-S1-mini的W4A16量化 Open

InternLM/lmdeploy#4402 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026

InternLM/lmdeploy

Get new issues in your inbox