InternLM/lmdeploy

lmdeploy

✅ Recently maintained

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

8,128Stars
772Forks
+117-day stars

Python · Apache-2.0 · Last push 2026-10-30

Official repository & installation ↗
cuda-kernelsdeepspeedfastertransformerllm-inferenceturbomindinternlmllamallmcodellamallama2

Star history

2025-09-292026-11-02
View historical data
DateStars
2026-10-048,088
2026-10-058,088
2026-10-068,088
2026-10-078,091
2026-10-088,091
2026-10-098,091
2026-10-108,092
2026-10-118,093
2026-10-128,094
2026-10-138,095
2026-10-148,095
2026-10-158,099
2026-10-168,099
2026-10-178,099
2026-10-188,101
2026-10-198,101
2026-10-208,104
2026-10-218,105
2026-10-228,109
2026-10-238,111
2026-10-248,112
2026-10-258,116
2026-10-268,121
2026-10-278,123
2026-10-288,124
2026-10-298,125
2026-10-308,126
2026-10-318,126
2026-11-018,126
2026-11-028,128

Get the project

git clone https://github.com/InternLM/lmdeploy.git

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

ollama

Run DeepSeek, Qwen, Gemma and other LLMs locally with one command, plus model management and an API.

★ 185,625vllm

High-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.

★ 96,103unsloth

Finetune Llama, Mistral and other LLMs 2-5x faster with 80% less memory.

★ 78,938