sgl-project / sglang
SGLang is a fast serving framework for large language models and vision language models.
☆14,392Updated this week
Alternatives and similar repositories for sglang
Users that are interested in sglang are comparing it to the libraries listed below
Sorting:
- A high-throughput and memory-efficient inference and serving engine for LLMs☆47,245Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,335Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆8,084Updated this week
- TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizati…☆10,476Updated this week
- Fast and memory-efficient exact attention☆17,346Updated last week
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆8,648Updated this week
- Large Language Model Text Generation Inference☆10,119Updated this week
- Train transformer language models with reinforcement learning.☆13,703Updated this week
- Retrieval and Retrieval-augmented LLMs☆9,610Updated last month
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,765Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,276Updated this week
- Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥☆38,553Updated this week
- FlashInfer: Kernel Library for LLM Serving☆2,966Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆7,020Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,221Updated this week
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆21,197Updated this week
- Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆10,354Updated last week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,482Updated last year
- A framework for few-shot evaluation of language models.☆8,904Updated last week
- The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.☆18,266Updated 2 weeks ago
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & LoRA & vLLM & RFT)☆6,661Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,430Updated 11 months ago
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆12,097Updated last week
- Tools for merging pretrained large language models.☆5,646Updated last week
- DSPy: The framework for programming—not prompting—language models☆24,189Updated this week
- High-speed Large Language Model Serving for Local Deployment☆8,200Updated 2 months ago
- Minimal reproduction of DeepSeek R1-Zero☆11,753Updated 3 weeks ago
- Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you ne…☆7,802Updated this week
- Go ahead and axolotl questions☆9,336Updated this week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, GLM4, Mistral, Yi1.5, DeepSeek-R1, ...) an…☆7,582Updated this week