awesome-repositories.com
Blog
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectAboutHow we rankPressMCP server
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
Infini-AI-Lab avatar

Infini-AI-Lab/TriForce

0
View on GitHub↗
281 stars·20 forks·Python·2 viewsinfini-ai-lab.github.io/TriForce↗

TriForce

[COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Features

  • Speculative Decoding - Hierarchical speculative decoding for lossless long-sequence acceleration.

Star history

Star history chart for infini-ai-lab/triforceStar history chart for infini-ai-lab/triforce

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Open-source alternatives to TriForce

Similar open-source projects, ranked by how many features they share with TriForce.
  • pytorch-labs/gpt-fastpytorch-labs avatar

    pytorch-labs/gpt-fast

    6,225View on GitHub↗

    gpt-fast is a PyTorch transformer inference engine designed for low-latency text generation. It functions as a distributed GPU inference library, a quantized model runner, and a speculative decoding framework. The system utilizes a speculative decoding workflow where a small draft model predicts token sequences for verification by a larger model to accelerate generation. It supports quantized model execution to reduce memory footprint and implements tensor parallelism to split computations across multiple GPUs. The project includes a standardized evaluation harness to measure the accuracy an

    Python
    View on GitHub↗6,225
  • meta-pytorch/gpt-fastmeta-pytorch avatar

    meta-pytorch/gpt-fast

    6,223View on GitHub↗

    gpt-fast is a PyTorch transformer inference engine designed for text generation using a native tensor library implementation. It provides a runtime for executing large language models without the need for external C++ extensions. The project implements speculative decoding to accelerate generation by using a small draft model for token prediction and a larger model for verification. It further optimizes performance through a compiled prefill stage and a multi-GPU tensor parallelism library that shards linear layers across multiple graphics processing units. Memory efficiency is managed throu

    Python
    View on GitHub↗6,223
  • fasterdecoding/medusaFasterDecoding avatar

    FasterDecoding/Medusa

    2,751View on GitHub↗

    Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

    Jupyter Notebook
    View on GitHub↗2,751
  • hao-ai-lab/lookaheaddecodinghao-ai-lab avatar

    hao-ai-lab/LookaheadDecoding

    1,336View on GitHub↗

    ICML 2024 Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

    Python
    View on GitHub↗1,336
See all 9 alternatives to TriForce→

Frequently asked questions

What does infini-ai-lab/triforce do?

[COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

What are the main features of infini-ai-lab/triforce?

The main features of infini-ai-lab/triforce are: Speculative Decoding.

What are some open-source alternatives to infini-ai-lab/triforce?

Open-source alternatives to infini-ai-lab/triforce include: pytorch-labs/gpt-fast — gpt-fast is a PyTorch transformer inference engine designed for low-latency text generation. It functions as a… meta-pytorch/gpt-fast — gpt-fast is a PyTorch transformer inference engine designed for text generation using a native tensor library… hao-ai-lab/lookaheaddecoding — [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding. infini-ai-lab/magicdec — [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding. leezythu/focusllm — FocusLLM: Scaling LLM’s Context by Parallel Decoding. smart-lty/parallelspeculativedecoding — [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length.