Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
☆1,009Jul 24, 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).☆2,478Feb 20, 2026Updated 5 months ago
- A PyTorch native library for training speculative decoding models☆205Jul 14, 2026Updated last week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆652Updated this week
- Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆123Updated this week
- Materials for learning SGLang☆861Jan 5, 2026Updated 6 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆314Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆401Apr 22, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,032Updated this week
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,281Jun 27, 2026Updated 3 weeks ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,789Updated this week
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆211Mar 18, 2026Updated 4 months ago
- slime is an LLM post-training framework for RL Scaling.☆7,629Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,999Updated this week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆170Dec 23, 2025Updated 7 months 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.
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆55Jul 15, 2025Updated last year
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,588Jul 14, 2026Updated last week
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆174Feb 27, 2026Updated 4 months ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,526May 10, 2026Updated 2 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆462Jul 14, 2026Updated last week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,628May 17, 2026Updated 2 months ago
- My learning notes for ML SYS.☆6,772Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆30,733Updated this week
- Perplexity GPU Kernels☆593Nov 7, 2025Updated 8 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.
- ☆696Jul 14, 2026Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,498Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆732Jul 4, 2026Updated 3 weeks ago
- SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models☆697Updated this week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆3,306Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,908Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆1,658Updated this week
- Allow torch tensor memory to be released and resumed later☆261Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,580Updated this week
- 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 fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,345Aug 28, 2025Updated 10 months ago
- 🚀 Efficient implementations for emerging model architectures☆5,414Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆6,767Jul 9, 2026Updated 2 weeks ago
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,106Updated this week
- A Quirky Assortment of CuTe Kernels☆1,070Updated this week
- High Performance LLM Inference Operator Library☆1,065Updated this week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,221Apr 8, 2026Updated 3 months ago