[NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning
☆69Oct 31, 2025Updated 10 months ago
Alternatives and similar repositories for LookaheadReasoning
Users that are interested in LookaheadReasoning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆105Apr 7, 2026Updated 5 months ago
- JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting☆217Aug 9, 2026Updated 3 weeks ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning☆67Dec 18, 2025Updated 8 months ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆64Oct 27, 2025Updated 10 months ago
- [ICML 2026] d3LLM: Ultra-Fast Diffusion LLM 🚀☆150May 1, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆233May 31, 2025Updated last year
- ☆34Oct 13, 2025Updated 10 months ago
- Pygloo provides Python bindings for Gloo.☆22Jul 7, 2025Updated last year
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆151Nov 10, 2025Updated 9 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆75Oct 2, 2025Updated 11 months ago
- Easy, Fast, and Scalable Multimodal AI☆130Jun 2, 2026Updated 3 months ago
- DeepConf: Deep Think with Confidence☆414Jul 17, 2026Updated last month
- ☆54May 19, 2025Updated last year
- When Reasoning Meets Its Laws☆38Jan 2, 2026Updated 8 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆20May 14, 2025Updated last year
- VibeRL is a Reinforcement Learning framework built essentially through vibe coding with Kimi K2.☆18Aug 31, 2026Updated last week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,151Updated this week
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆67Mar 5, 2025Updated last year
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆40Aug 31, 2026Updated last week
- ☆13Jan 7, 2025Updated last year
- ⚡️Qwen-Image 4.8x🎉 speedup with Hybrid Acceleration for low VRAM GPUs☆17Oct 24, 2025Updated 10 months ago
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆32Oct 20, 2025Updated 10 months ago
- Cavs: An Efficient Runtime System for Dynamic Neural Networks☆15Sep 18, 2020Updated 5 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Scale digital agent rollouts without pain.☆36Jun 18, 2026Updated 2 months ago
- [NeurIPS 2025] Multipole Attention for Efficient Long Context Reasoning☆25Dec 5, 2025Updated 9 months ago
- Empowering LLM Agents for Real-World Computer System Optimization☆17Sep 10, 2025Updated 11 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆83Nov 4, 2024Updated last year
- (ICPP '20) ShadowTutor: Distributed Partial Distillation for Mobile Video DNN Inference☆12Jun 22, 2020Updated 6 years ago
- ☆22May 23, 2025Updated last year
- Autonomous GPU kernel optimization system driven by AI agents.☆31Mar 29, 2026Updated 5 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆308Nov 7, 2025Updated 10 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆758Aug 29, 2026Updated last week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆55Jun 17, 2025Updated last year
- Xmixers: A collection of SOTA efficient token/channel mixers☆29Sep 4, 2025Updated last year
- ☆385Jan 28, 2026Updated 7 months ago
- Distributed ML Optimizer☆35Jul 28, 2021Updated 5 years ago
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆219Mar 18, 2026Updated 5 months ago
- [ICML 2026] Jacobi Forcing: Fast and Accurate Diffusion-style Decoding☆120Feb 20, 2026Updated 6 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆478Updated this week