inclusionAI / asystem-awexLinks
A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows
☆118Updated 2 weeks ago
Alternatives and similar repositories for asystem-awex
Users that are interested in asystem-awex are comparing it to the libraries listed below
Sorting:
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆256Updated last month
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆250Updated 3 weeks ago
- Toolchain built around the Megatron-LM for Distributed Training☆81Updated last month
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆481Updated last month
- The driver for LMCache core to run in vLLM☆59Updated 11 months ago
- torchcomms: a modern PyTorch communications API☆315Updated last week
- KV cache store for distributed LLM inference☆378Updated last month
- ☆654Updated last week
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆56Updated 2 months ago
- ☆96Updated 9 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆885Updated this week
- ☆30Updated 3 weeks ago
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆232Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆352Updated this week
- Perplexity open source garden for inference technology☆321Updated 2 weeks ago
- LLM Serving Performance Evaluation Harness☆82Updated 10 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆363Updated last week
- HuggingFace conversion and training library for Megatron-based models☆324Updated this week
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆110Updated last month
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆177Updated 2 weeks ago
- Perplexity GPU Kernels☆548Updated 2 months ago
- Efficient and easy multi-instance LLM serving☆519Updated 4 months ago
- JAX backend for SGL☆205Updated last week
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆73Updated last week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆597Updated last week
- ☆337Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆204Updated last year
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆182Updated this week
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆77Updated 3 weeks ago