A PyTorch native library for training speculative decoding models
☆84Apr 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:
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆54Jul 15, 2025Updated 9 months ago
- A collection of reproducible inference engine benchmarks☆38Apr 22, 2025Updated 11 months ago
- end-to-end voicebot that answers open domain questions.☆10Oct 23, 2021Updated 4 years ago
- Optimized primitives for collective multi-GPU communication☆25Apr 17, 2024Updated 2 years ago
- LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding☆37Updated this week
- 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.
- ☆17Mar 8, 2020Updated 6 years ago
- Parallel Computing -- Validation Suite: Validation engine for Exascale project benchmarks☆16Mar 26, 2026Updated 3 weeks ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated 8 months ago
- A TUI-based utility for real-time monitoring of InfiniBand traffic and performance metrics on the local node☆64Dec 19, 2025Updated 4 months ago
- SAM 2++: Tracking Anything at Any Granularity☆60Dec 15, 2025Updated 4 months ago
- ☆34Apr 8, 2025Updated last year
- CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning☆36Aug 28, 2025Updated 7 months ago
- ☆52Updated this week
- Paper collection of next-generation network resource allocation by machine learning☆11Mar 18, 2020Updated 6 years 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.
- ☆11Dec 20, 2022Updated 3 years ago
- ☆11Jan 6, 2020Updated 6 years ago
- ☆12Nov 21, 2017Updated 8 years ago
- High Performance KV Cache Store for LLM☆53Apr 6, 2026Updated last week
- ☆22Dec 15, 2023Updated 2 years ago
- Predict whether the protien sequence and the drug SMILES will be interact with each other☆13Apr 25, 2019Updated 6 years ago
- An unofficial copy of MIT's Alloy Analyzer model checking tool.☆20May 30, 2013Updated 12 years ago
- Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tools☆192Updated this week
- ☆23Aug 21, 2025Updated 7 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.
- Write yourself a simply-typed lambda calculus using Rust in a week!☆13May 13, 2024Updated last year
- Residual Context Diffusion (RCD): Repurposing discarded signals as structured priors for high-performance reasoning in dLLMs.☆57Mar 12, 2026Updated last month
- Project is intended to build and deploy an scene detection application onto Qualcomm Robotics development Kit (RB5) that detects whether …☆10Jun 26, 2022Updated 3 years ago
- PersoSim - the open source eID simulator☆16Nov 13, 2025Updated 5 months ago
- ☆13Dec 4, 2017Updated 8 years ago
- Code for "What really matters in matrix-whitening optimizers?"☆23Oct 31, 2025Updated 5 months ago
- Graph-indexed Pandas DataFrames for analyzing hierarchical performance data☆35Mar 6, 2026Updated last month
- 主要是高扬《白话机器学习》的相关内容，作业以及推荐资料汇总☆25Feb 4, 2019Updated 7 years ago
- Game Engine From Scratch -- Rust China Conference 2020 topic by LemonHX and his team.☆14Dec 16, 2020Updated 5 years ago
- 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.
- NVIDIA's launch, startup, and logging scripts used by our MLPerf Training and HPC submissions☆40Sep 12, 2025Updated 7 months ago
- Persistent dense gemm for Hopper in `CuTeDSL`☆15Aug 9, 2025Updated 8 months ago
- ☆15Mar 16, 2018Updated 8 years ago
- [CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning☆73Mar 25, 2026Updated 3 weeks ago
- An IR for efficiently simulating distributed ML computation.☆33Jan 13, 2024Updated 2 years ago
- Audio samples for the paper 'Phase-aware music super-resolution using generative adversarial networks'☆14May 15, 2020Updated 5 years ago
- Codes for accepted paper "Cooperative Pruning in Cross-Domain Deep Neural Network Compression" in IJCAI 2019.☆12Aug 15, 2019Updated 6 years ago