skypilot-org / skypilot
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 16+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
☆8,026Updated this week
Alternatives and similar repositories for skypilot:
Users that are interested in skypilot are comparing it to the libraries listed below
- Large Language Model Text Generation Inference☆10,081Updated this week
- Structured Text Generation☆11,525Updated last week
- Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)☆12,041Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,872Updated 9 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆46,456Updated this week
- Go ahead and axolotl questions☆9,258Updated this week
- Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.☆11,216Updated last week
- Adding guardrails to large language models.☆4,877Updated last week
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,391Updated 9 months ago
- the AI-native open-source embedding database☆19,694Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆12,076Updated this week
- Semantic cache for LLMs. Fully integrated with LangChain and llama_index.☆7,532Updated 7 months ago
- A guidance language for controlling large language models.☆20,126Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,417Updated 10 months ago
- 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading☆9,605Updated 8 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆13,976Updated this week
- A Bulletproof Way to Generate Structured JSON from Language Models☆4,715Updated last year
- Tensor library for machine learning☆12,445Updated this week
- A framework for few-shot evaluation of language models.☆8,855Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,463Updated last year
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,482Updated last year
- Tools for merging pretrained large language models.☆5,628Updated this week
- A language for constraint-guided and efficient LLM programming.☆3,922Updated 11 months ago
- PyTorch native post-training library☆5,154Updated this week
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆2,965Updated this week
- structured outputs for llms☆10,311Updated this week
- Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.☆11,059Updated last week
- [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which ach…☆5,048Updated last month
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆14,358Updated last month
- Python bindings for llama.cpp☆9,030Updated 3 weeks ago