MoonshotAI / checkpoint-engineLinks
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
☆888Updated this week
Alternatives and similar repositories for checkpoint-engine
Users that are interested in checkpoint-engine are comparing it to the libraries listed below
Sorting:
- ☆686Updated this week
- ☆949Updated 2 months ago
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆484Updated last month
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆368Updated last week
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆547Updated this week
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆258Updated last month
- PyTorch-native post-training at scale☆585Updated this week
- Scalable toolkit for efficient model reinforcement☆1,210Updated this week
- LLM KV cache compression made easy☆749Updated 3 weeks ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆467Updated 7 months ago
- Block Diffusion for Ultra-Fast Speculative Decoding☆188Updated last week
- Efficient LLM Inference over Long Sequences☆393Updated 6 months ago
- Perplexity GPU Kernels☆552Updated 2 months ago
- Async RL Training at Scale☆985Updated this week
- dInfer: An Efficient Inference Framework for Diffusion Language Models☆385Updated last week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆615Updated last week
- ☆1,257Updated last month
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,437Updated this week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆251Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆748Updated this week
- Materials for learning SGLang☆714Updated last week
- Accelerating MoE with IO and Tile-aware Optimizations☆522Updated last week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆519Updated 11 months ago
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆245Updated this week
- Common recipes to run vLLM☆327Updated this week
- ☆443Updated 5 months ago
- Training library for Megatron-based models with bi-directional Hugging Face conversion capability☆347Updated this week
- Serverless LLM Serving for Everyone.☆631Updated this week
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆267Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆936Updated 2 months ago