[NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
☆235May 31, 2025Updated last year
Alternatives and similar repositories for Dynasor
Users that are interested in Dynasor are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 🚀 First survey bridging LLM, RL, and Agentic Eras — 100+ papers on efficient inference from static generation to systematic reasoning an…☆15May 13, 2026Updated 5 months ago
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆69Aug 22, 2026Updated 2 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆106Apr 7, 2026Updated 6 months ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning☆67Dec 18, 2025Updated 10 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆56Oct 29, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆69Oct 31, 2025Updated last year
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆186Feb 27, 2026Updated 8 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆76Oct 2, 2025Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆85Nov 4, 2024Updated last year
- ☆12May 11, 2025Updated last year
- ☆69Dec 3, 2024Updated last year
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆18Jun 30, 2025Updated last year
- ☆14Jun 10, 2025Updated last year
- DeepConf: Deep Think with Confidence☆417Jul 17, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆316May 1, 2025Updated last year
- ☆27May 14, 2026Updated 5 months ago
- JetSpec++/JetSpec: Causal Parallel (Tree) Drafting with Self Refinement☆254Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆161Dec 4, 2024Updated last year
- ☆763Dec 23, 2025Updated 10 months ago
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆792Oct 20, 2026Updated last week
- ☆20Mar 18, 2026Updated 7 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆494Sep 23, 2026Updated last month
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,231Oct 10, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,345Mar 6, 2025Updated last year
- ☆56Jul 7, 2025Updated last year
- [NeurIPS 2025] The implementation of paper "On Reasoning Strength Planning in Large Reasoning Models"☆33Jul 6, 2025Updated last year
- Code of the research paper "SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm"☆14Jul 8, 2026Updated 3 months ago
- A selective knowledge distillation algorithm for efficient speculative decoders☆39Nov 27, 2025Updated 11 months ago
- Compact and Agent-Native MoE Training System☆359Updated this week
- ☆32May 24, 2025Updated last year
- ☆32Mar 24, 2025Updated last year
- [COLM 2026] Resa: Transparent Reasoning Models via SAEs☆49Sep 23, 2025Updated last year
- 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.
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆314Dec 1, 2025Updated 11 months ago
- ☆21Jun 27, 2024Updated 2 years ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆67Oct 27, 2025Updated last year
- Some microbenchmarks and design docs before commencement☆11Feb 1, 2021Updated 5 years ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆256Dec 16, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆976Mar 29, 2026Updated 7 months ago
- Official Repo for Open-Reasoner-Zero☆2,100Jun 2, 2025Updated last year