A lightweight inference engine supporting speculative speculative decoding (SSD).
☆1,021May 10, 2026Updated 6 months ago
Alternatives and similar repositories for ssd
Users that are interested in ssd are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,247Aug 18, 2026Updated 3 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,290Updated this week
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆227Mar 18, 2026Updated 8 months ago
- ☆396Apr 16, 2026Updated 7 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 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.
- TokenSpeed is a speed-of-light LLM inference engine.☆2,941Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,581Feb 20, 2026Updated 9 months ago
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆141Jul 25, 2026Updated 3 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,958Updated this week
- Tile primitives for speedy kernels☆3,803Sep 12, 2026Updated 2 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆123Dec 2, 2025Updated 11 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆316Updated this week
- Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.☆1,631Updated this week
- A Quirky Assortment of CuTe Kernels☆1,196Oct 30, 2026Updated 3 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆967Updated this week
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆187Feb 27, 2026Updated 8 months ago
- PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation (ICLR 26)☆38Jun 10, 2026Updated 5 months ago
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,317Jul 9, 2026Updated 4 months ago
- ☆46Oct 15, 2025Updated last year
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,904Sep 24, 2026Updated last month
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,366Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆9,006Updated this week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆175Dec 23, 2025Updated 10 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,597Oct 19, 2026Updated last month
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,869Updated this week
- Kernels, of the mega variety :)☆884May 26, 2026Updated 5 months ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,309Jun 27, 2026Updated 4 months ago
- A kernel library written in tilelang☆2,078Oct 14, 2026Updated last month
- slime is an LLM training framework for RL Scaling.☆8,849Nov 5, 2026Updated 2 weeks ago
- 🚀 Efficient implementations for emerging model architectures☆6,066Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,623Updated this week
- A PyTorch native library for training speculative decoding models☆268Updated this week
- 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.
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆346Aug 19, 2026Updated 3 months ago
- high-performance linear attention kernel library built on TileLang☆760Oct 30, 2026Updated 3 weeks ago
- Efficient Triton Kernels for LLM Training☆6,706Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,398Updated this week
- ☆552Aug 26, 2026Updated 2 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆498Sep 23, 2026Updated last month
- LLM KV cache compression made easy☆1,259Updated this week
Are these results useful?