PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
☆77Oct 2, 2025Updated last year
Alternatives and similar repositories for specreason
Users that are interested in specreason are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆34Oct 13, 2025Updated last year
- Artifact for "Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs" [arXiv '25]☆21Jul 26, 2026Updated 3 months ago
- [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.☆58May 2, 2025Updated last year
- ☆20May 14, 2025Updated last year
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆36Sep 12, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆20Mar 18, 2026Updated 7 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆74Mar 5, 2025Updated last year
- Simulator for SpecDecode Bench☆14Apr 1, 2026Updated 7 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆122Dec 2, 2025Updated 11 months ago
- ☆52Sep 13, 2025Updated last year
- [NeurIPS 2025] Official PyTorch implementation for the paper AutoJudge: Judge Decoding Without Manual Annotation☆21Dec 22, 2025Updated 10 months ago
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆18Jun 30, 2025Updated last year
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆65Apr 6, 2025Updated last year
- ☆11Oct 29, 2026Updated last week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆280Aug 31, 2024Updated 2 years ago
- ☆15Nov 7, 2024Updated last year
- [NeurIPS 2025] RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models☆12Oct 6, 2026Updated last month
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆173Dec 23, 2025Updated 10 months ago
- Quantization in the Jagged Loss Landscape of Vision Transformers☆14Oct 22, 2023Updated 3 years ago
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆32Oct 20, 2025Updated last year
- Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs☆28Jun 25, 2024Updated 2 years ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆90Sep 15, 2025Updated last year
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆86Jul 14, 2025Updated last year
- 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.☆235May 31, 2025Updated last year
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆69Aug 22, 2026Updated 2 months ago
- Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"☆31Apr 17, 2026Updated 6 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆70Oct 31, 2025Updated last year
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆187Feb 27, 2026Updated 8 months ago
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆68Sep 27, 2025Updated last year
- ☆14Mar 20, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆356Jun 12, 2026Updated 4 months ago
- ☆12Oct 14, 2025Updated last year
- [ICLR 2026] LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation☆14Mar 16, 2026Updated 7 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆162Dec 4, 2024Updated last year
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆56Mar 14, 2025Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆106Apr 7, 2026Updated 6 months ago
- ☆19Jun 3, 2023Updated 3 years ago