deepseek-ai / LPLBLinks
An early research stage expert-parallel load balancer for MoE models based on linear programming.
☆495Updated 2 months ago
Alternatives and similar repositories for LPLB
Users that are interested in LPLB are comparing it to the libraries listed below
Sorting:
- Perplexity GPU Kernels☆560Updated 3 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆569Updated 3 weeks ago
- torchcomms: a modern PyTorch communications API☆327Updated last week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆564Updated 2 weeks ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆391Updated this week
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆462Updated last month
- Perplexity open source garden for inference technology☆359Updated last month
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆263Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆902Updated last week
- Autonomous GPU Kernel Generation via Deep Agents☆228Updated this week
- Block Diffusion for Ultra-Fast Speculative Decoding☆459Updated last week
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆269Updated last week
- dInfer: An Efficient Inference Framework for Diffusion Language Models☆410Updated last month
- Code for data-aware compression of DeepSeek models☆70Updated 2 months ago
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆112Updated last month
- Ship correct and fast LLM kernels to PyTorch☆140Updated 3 weeks ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆87Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆279Updated last week
- JAX backend for SGL☆234Updated this week
- KV cache compression for high-throughput LLM inference☆153Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆141Updated last year
- Building the Virtuous Cycle for AI-driven LLM Systems☆151Updated last week
- kernels, of the mega variety☆665Updated last week
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆248Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆458Updated 8 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆209Updated last year
- ☆342Updated 2 weeks ago
- LLM KV cache compression made easy☆876Updated 2 weeks ago
- TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels☆194Updated this week
- Learning TileLang with 10 puzzles!☆118Updated last week