A PyTorch native library for training speculative decoding models
☆239Sep 2, 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.☆1,147Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆2,087Updated this week
- Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini &…☆503Updated this week
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆138Jul 25, 2026Updated last month
- ☆77Apr 30, 2026Updated 4 months ago
- 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.
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆799Updated this week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆325Jul 29, 2026Updated last month
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆219Mar 18, 2026Updated 5 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,418Updated this week
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆28May 12, 2026Updated 3 months ago
- ☆785Aug 23, 2026Updated last week
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆177Feb 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…☆502Updated this week
- mKernel: fast multi-node, multi-GPU fused kernels☆270Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆219Updated this week
- IREE Tokenizer Python Bindings☆21Mar 5, 2026Updated 5 months ago
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,070Jul 9, 2026Updated last month
- ☆41Jun 23, 2026Updated 2 months ago
- Perplexity GPU Kernels☆605Nov 7, 2025Updated 9 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,326Updated this week
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆53May 12, 2026Updated 3 months ago
- ☆419Jul 30, 2026Updated last month
- An LLM post-training framework with vLLM for RL Scaling☆449Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆396Apr 16, 2026Updated 4 months ago
- htop-like TUI for real-time RDMA network monitoring.☆85Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,749Aug 13, 2026Updated 3 weeks ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,524Feb 20, 2026Updated 6 months ago
- ☆99Sep 15, 2025Updated 11 months ago
- An Optimizer for Nvidia Compilers.☆130Aug 28, 2026Updated last week
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,292Jun 27, 2026Updated 2 months ago
- ☆98Mar 26, 2025Updated last year
- A high-performance and light-weight router for vLLM large scale deployment☆394Updated this week
- 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☆1,140Aug 28, 2026Updated last week
- slime is an LLM post-training framework for RL Scaling.☆8,368Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆39Updated this week
- XoRL☆44Aug 27, 2026Updated last week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆410Apr 22, 2025Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,476Updated this week
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,081Updated this week