PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
☆75Oct 2, 2025Updated 10 months ago
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 10 months ago
- ☆20May 14, 2025Updated last year
- Artifact for "Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs" [arXiv '25]☆21Jul 26, 2026Updated 2 weeks ago
- [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.☆56May 2, 2025Updated last year
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆35Sep 12, 2025Updated 11 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆67Mar 5, 2025Updated last year
- ☆49Sep 13, 2025Updated 11 months ago
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆17Jun 30, 2025Updated last year
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆32Oct 20, 2025Updated 9 months ago
- [NeurIPS 2025] Official PyTorch implementation for the paper AutoJudge: Judge Decoding Without Manual Annotation☆21Dec 22, 2025Updated 7 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆117Dec 2, 2025Updated 8 months ago
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆62Apr 6, 2025Updated last year
- ☆20Mar 18, 2026Updated 4 months ago
- Quantization in the Jagged Loss Landscape of Vision Transformers☆13Oct 22, 2023Updated 2 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆15Nov 7, 2024Updated 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
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆171Dec 23, 2025Updated 7 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆87Sep 15, 2025Updated 10 months ago
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆86Jul 14, 2025Updated last year
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆232May 31, 2025Updated last year
- Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"☆30Apr 17, 2026Updated 3 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆22Nov 28, 2025Updated 8 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 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.
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆175Feb 27, 2026Updated 5 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆69Oct 31, 2025Updated 9 months ago
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆67Sep 27, 2025Updated 10 months ago
- Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆348Jun 12, 2026Updated 2 months ago
- DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning☆18Nov 11, 2025Updated 9 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆281Aug 31, 2024Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆105Apr 7, 2026Updated 4 months ago
- Minimal PyTorch implementation of TP, SP, FSDP and sharded-EMA☆32Nov 27, 2025Updated 8 months ago
- ☆19Jun 3, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- The offical repo for "Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing"☆19Feb 3, 2026Updated 6 months ago
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆425Nov 20, 2025Updated 8 months ago
- [EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study un…☆19Dec 17, 2025Updated 7 months ago
- NVFP4 Flash-Attention 4 on BlackWell☆39Jul 23, 2026Updated 3 weeks ago
- [ASPLOS' 26] TetriServe: Efficiently Serving Mixed DiT Workloads☆17Mar 12, 2026Updated 5 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆87Jul 11, 2025Updated last year