Slow-Fast Inference: Training-free Inference Acceleration via Within-sentence Support Stability
☆18Jul 14, 2026Updated this week
Alternatives and similar repositories for SFI
Users that are interested in SFI are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.☆18Mar 31, 2026Updated 3 months ago
- 基于Funasr的[实时]AI语音助手☆25Dec 18, 2025Updated 6 months ago
- Directed masked autoencoders☆14Mar 25, 2026Updated 3 months ago
- Code for paper: Long cOntext aliGnment via efficient preference Optimization☆26Oct 10, 2025Updated 9 months ago
- Third-party test scripts and bug tracking for SCALE☆36Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆21Feb 9, 2020Updated 6 years ago
- ☆21Mar 22, 2023Updated 3 years ago
- DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention☆21May 25, 2026Updated last month
- ☆23Updated this week
- `swarmd` is a multi-tenant runtime for running background Agents in a safe and secure manner. Agents are defined in YAML and run as gorou…☆31Jun 25, 2026Updated 3 weeks ago
- C# wrapper for msnhnet.☆10Aug 14, 2020Updated 5 years ago
- Github老玩家自己搭的服务器，老飞飞原版，可联机-天马座☆10May 14, 2019Updated 7 years ago
- ☆12Mar 13, 2023Updated 3 years ago
- WaveTuner is an Android NeuroFeedback app using a Neurosky Mindwave Mobile to train your brain.☆20Jan 2, 2014Updated 12 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆29Aug 30, 2024Updated last year
- Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200☆121Feb 28, 2026Updated 4 months ago
- ☆11Dec 26, 2025Updated 6 months ago
- 高性能短序列稀疏Mask Attention CUDA算子，针对<1K序列+75%稀疏度优化☆79Mar 18, 2026Updated 3 months ago
- ☆47Oct 16, 2025Updated 9 months ago
- ☆16Nov 21, 2017Updated 8 years ago
- Inference Llama 2 in one file of pure go☆15Jul 25, 2023Updated 2 years ago
- Convert Scala Language Specification markdown files to pdf / epub format☆12Oct 6, 2019Updated 6 years ago
- TensorFlow Implementation of Several Zero-Shot Image Style Transfer Methods☆15Sep 30, 2017Updated 8 years 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.
- Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Juli…☆12Aug 13, 2020Updated 5 years ago
- ☆11Aug 23, 2015Updated 10 years ago
- ☆12Aug 10, 2022Updated 3 years ago
- ☆12Sep 30, 2017Updated 8 years ago
- Code release for Learning to Assemble Neural Module Tree Networks for Visual Grounding (ICCV 2019)☆39Nov 23, 2019Updated 6 years ago
- Colab notebooks from Launch Data Science at HackCville☆13Jun 14, 2019Updated 7 years ago
- Accelerating CNN's convolution operation on GPUs by using memory-efficient data access patterns.☆14Dec 8, 2017Updated 8 years ago
- MXNet implementation of AC-BLSTM☆23Apr 3, 2019Updated 7 years ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆39Feb 29, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Play with Wasserstein GAN on MXNet.☆10Mar 3, 2017Updated 9 years ago
- Asymmetric Convolutional Bidirectional LSTM Networks for Text Classification☆11Mar 26, 2018Updated 8 years ago
- Memory-efficient optimum einsum using opt_einsum planning and PyTorch kernels.☆16Apr 24, 2023Updated 3 years ago
- ☆17Jan 1, 2024Updated 2 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆56Aug 6, 2025Updated 11 months ago
- [ICLR 2025, IEEE TPAMI 2026] Mixture Compressor & MC#☆75Feb 12, 2025Updated last year
- Implement some method of LLM KV Cache Sparsity☆41Jun 6, 2024Updated 2 years ago