hao-ai-lab / LookaheadReasoningLinks
[NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning
☆50Updated last month
Alternatives and similar repositories for LookaheadReasoning
Users that are interested in LookaheadReasoning are comparing it to the libraries listed below
Sorting:
- ☆101Updated 5 months ago
- ☆130Updated 4 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆86Updated 2 weeks ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆46Updated 3 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆147Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 10 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆195Updated 4 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆197Updated 4 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- JAX backend for SGL☆78Updated this week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated last month
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆41Updated last month
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆119Updated 4 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆50Updated last year
- ☆120Updated 2 months ago
- KV cache compression for high-throughput LLM inference☆142Updated 8 months ago
- ☆50Updated 5 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆260Updated 3 weeks ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆147Updated 3 months ago
- Make SGLang go brrr☆36Updated 3 weeks ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆222Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- Hydragen: High-Throughput LLM Inference with Shared Prefixes☆43Updated last year
- ☆145Updated 8 months ago
- Quantized Attention on GPU☆44Updated 11 months ago
- ☆96Updated 6 months ago
- Fast and memory-efficient exact attention☆71Updated 7 months ago
- The evaluation framework for training-free sparse attention in LLMs☆101Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆125Updated 4 months ago