MoonshotAI / checkpoint-engineLinks
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
☆516Updated 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:
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆235Updated this week
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆438Updated 3 months ago
- ☆423Updated this week
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆243Updated 2 months ago
- Efficient LLM Inference over Long Sequences☆391Updated 2 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆123Updated last month
- Simple & Scalable Pretraining for Neural Architecture Research☆291Updated 3 weeks ago
- KV cache compression for high-throughput LLM inference☆136Updated 7 months ago
- Simple extension on vLLM to help you speed up reasoning model without training.☆188Updated 3 months ago
- Scalable toolkit for efficient model reinforcement☆843Updated last week
- Decentralized RL Training at Scale☆569Updated this week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆343Updated 9 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆245Updated 7 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆188Updated 2 months ago
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆208Updated last week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆490Updated 7 months ago
- Tina: Tiny Reasoning Models via LoRA☆281Updated 3 weeks ago
- Common recipes to run vLLM☆123Updated last week
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆233Updated 8 months ago
- rl from zero pretrain, can it be done? yes.☆265Updated 3 weeks ago
- ☆153Updated last month
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆140Updated this week
- LLM KV cache compression made easy☆604Updated this week
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated this week
- ☆217Updated 7 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆818Updated this week
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆333Updated 4 months ago
- Memory optimized Mixture of Experts☆62Updated last month
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆269Updated last month
- Storing long contexts in tiny caches with self-study☆179Updated last week