A PyTorch native library for training speculative decoding models
☆249Sep 19, 2026Updated this week
Alternatives and similar repositories for TorchSpec
Users that are interested in TorchSpec are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,189Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆2,164Updated this week
- Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini &…☆543Updated this week
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆138Jul 25, 2026Updated last month
- ☆79Apr 30, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆850Updated this week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆331Jul 29, 2026Updated last month
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆221Mar 18, 2026Updated 6 months ago
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆28May 12, 2026Updated 4 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,979Updated this week
- ☆870Updated this week
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆179Feb 27, 2026Updated 6 months ago
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆511Updated this week
- mKernel: fast multi-node, multi-GPU fused kernels☆281Updated 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.
- IREE Tokenizer Python Bindings☆21Mar 5, 2026Updated 6 months ago
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆236Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,150Jul 9, 2026Updated 2 months ago
- ☆41Jun 23, 2026Updated 3 months ago
- Perplexity GPU Kernels☆608Nov 7, 2025Updated 10 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,495Updated this week
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆54May 12, 2026Updated 4 months ago
- ☆423Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆475Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆397Apr 16, 2026Updated 5 months ago
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,263Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,794Aug 13, 2026Updated last month
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,540Feb 20, 2026Updated 7 months ago
- ☆97Sep 15, 2025Updated last year
- htop-like TUI for real-time RDMA network monitoring.☆106Updated this week
- An Optimizer for Nvidia Compilers.☆136Updated this week
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,297Jun 27, 2026Updated 2 months ago
- ☆98Mar 26, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- High Performance LLM Inference Operator Library☆1,167Sep 7, 2026Updated 2 weeks ago
- slime is an LLM post-training framework for RL Scaling.☆8,524Updated this week
- A high-performance and light-weight router for vLLM large scale deployment☆436Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆43Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆414Apr 22, 2025Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,647Updated this week
- Materials for learning SGLang☆893Jan 5, 2026Updated 8 months ago