Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
☆1,213Oct 10, 2026Updated this week
Alternatives and similar repositories for SpecForge
Users that are interested in SpecForge are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,550Feb 20, 2026Updated 7 months ago
- A PyTorch native library for training speculative decoding models☆258Sep 29, 2026Updated 2 weeks ago
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆876Updated this week
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆139Jul 25, 2026Updated 2 months ago
- Materials for learning SGLang☆898Jan 5, 2026Updated 9 months 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.
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆331Jul 29, 2026Updated 2 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆415Apr 22, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,594Updated this week
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,298Jun 27, 2026Updated 3 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,108Updated this week
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆223Mar 18, 2026Updated 6 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,773Updated this week
- slime is an LLM post-training framework for RL Scaling.☆8,654Updated this week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆172Dec 23, 2025Updated 9 months ago
- 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.
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆56Jul 15, 2025Updated last year
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,859Sep 24, 2026Updated 2 weeks ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆182Feb 27, 2026Updated 7 months ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,268May 17, 2026Updated 4 months ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,152Aug 18, 2026Updated last month
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆489Sep 23, 2026Updated 3 weeks ago
- My learning notes for ML SYS.☆7,496Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆37,085Updated this week
- ☆967Updated 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.
- Perplexity GPU Kernels☆608Nov 7, 2025Updated 11 months ago
- Distributed Compiler and Optimized Parallel Kernels☆1,566Sep 18, 2026Updated 3 weeks ago
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,433Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆779Aug 29, 2026Updated last month
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆5,295Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,594Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆2,217Updated this week
- Allow torch tensor memory to be released and resumed later☆279Sep 29, 2026Updated 2 weeks ago
- State-of-the-art LLM compression, built for production inference with vLLM☆3,864Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,371Aug 28, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆5,855Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,216Jul 9, 2026Updated 3 months ago
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,236Updated this week
- A Quirky Assortment of CuTe Kernels☆1,173Sep 17, 2026Updated 3 weeks ago
- High Performance LLM Inference Operator Library☆1,175Sep 7, 2026Updated last month
- NVIDIA Inference Xfer Library (NIXL)☆1,299Updated this week