A PyTorch native library for training speculative decoding models
☆266Oct 29, 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.☆1,252Updated this week
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆140Jul 25, 2026Updated 3 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆2,841Updated this week
- Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini &…☆699Updated this week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆934Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆84Updated this week
- ☆81Apr 30, 2026Updated 6 months ago
- An LLM post-training framework with vLLM for RL Scaling☆496Updated this week
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆224Mar 18, 2026Updated 7 months ago
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆33May 12, 2026Updated 5 months ago
- Code for the paper ReplaySSM: Cache SSM Inputs, Not State☆63Oct 13, 2026Updated 3 weeks ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆332Oct 14, 2026Updated 2 weeks ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆186Feb 27, 2026Updated 8 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,253Updated 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.
- ☆538Aug 26, 2026Updated 2 months ago
- The official repo of "Draft-OPD: On-Policy Distillation for Speculative Draft Models"☆83Sep 4, 2026Updated 2 months ago
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,277Jul 9, 2026Updated 3 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆306Oct 17, 2026Updated 2 weeks ago
- Open Source AI Accelerator Research Platform Standard / 开源推理研究平台☆1,956Updated this week
- Fused MoE kernel☆23Oct 23, 2026Updated last week
- ☆1,098Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,840Updated this week
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆346Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,884Sep 24, 2026Updated last month
- Benchmark SGLang on SLURM☆25Apr 20, 2026Updated 6 months ago
- ☆11May 21, 2026Updated 5 months ago
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆523Updated this week
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,517Oct 19, 2026Updated 2 weeks ago
- Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average…☆317Sep 12, 2026Updated last month
- ☆434Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,568Feb 20, 2026Updated 8 months ago
- ☆78Sep 30, 2026Updated last month
- 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.
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,953Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆415Apr 22, 2025Updated last year
- slime is an LLM training framework for RL Scaling.☆8,774Oct 27, 2026Updated last week
- ☆12Aug 1, 2026Updated 3 months ago
- 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆1,068Updated this week
- A unified, torch-native training framework for MTP and block-parallel speculative decoding.☆285Jul 31, 2026Updated 3 months ago
- Simulator for SpecDecode Bench☆14Apr 1, 2026Updated 7 months ago