Slow-Fast Inference: Training-free Inference Acceleration via Within-sentence Support Stability
☆19Sep 2, 2026Updated last month
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:
- OpenCV Python wrapper example for CUDA function☆11Jan 5, 2022Updated 4 years ago
- Gaussian Embedding of Large-scale Attributed Graphs☆10Mar 13, 2020Updated 6 years ago
- HEtero-Assists Distillation for Heterogeneous Object Detectors☆10Jul 3, 2023Updated 3 years ago
- [NeurIPS 2025 Spotlight] Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning☆21Nov 14, 2025Updated 10 months ago
- This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.☆18Mar 31, 2026Updated 6 months 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.
- pure go for rwkv☆18Dec 31, 2023Updated 2 years ago
- Go implementation of Recursive Language Models (RLM) - inference-time scaling for arbitrarily long contexts☆21May 12, 2026Updated 4 months ago
- ☆15Sep 5, 2022Updated 4 years ago
- Directed masked autoencoders☆14Mar 25, 2026Updated 6 months ago
- Overflow Prevention Enhances Long-Context Recurrent LLMs (COLM 2025)☆18Jul 8, 2025Updated last year
- This is a sample implementation of "Billion-scale Network Embedding with Iterative Random Projection" (ICDM 2018).☆18Aug 5, 2020Updated 6 years ago
- ☆18Dec 22, 2025Updated 9 months ago
- PIC API☆25Sep 18, 2019Updated 7 years ago
- GPU monitor for Linux terminal supporting single or multiple gpu's in realtime☆20Jul 19, 2026Updated 2 months 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.
- ☆21Feb 9, 2020Updated 6 years ago
- pytorch implementation of DeepSeek Engram☆19Mar 24, 2026Updated 6 months ago
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆19Jul 10, 2025Updated last year
- ☆20Sep 17, 2026Updated 2 weeks ago
- DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention☆23May 25, 2026Updated 4 months ago
- This is the repo for the paper Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining.☆49Aug 22, 2025Updated last year
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 8 months ago
- C# wrapper for msnhnet.☆10Aug 14, 2020Updated 6 years ago
- ☆14Mar 26, 2020Updated 6 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.
- ☆12Mar 13, 2023Updated 3 years ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆25Oct 5, 2024Updated 2 years ago
- fast randomized SVD and its application to SVT algorithm☆26Feb 2, 2023Updated 3 years ago
- ☆20Mar 11, 2025Updated last year
- 基于Funasr的[实时]AI语音助手☆26Dec 18, 2025Updated 9 months ago
- `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…☆32Sep 23, 2026Updated last week
- ☆11Dec 26, 2025Updated 9 months ago
- [NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆78Sep 19, 2025Updated last year
- ☆16Nov 21, 2017Updated 8 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆97Sep 15, 2025Updated last year
- State tuning tunes the state☆34Feb 12, 2025Updated last year
- Convert Scala Language Specification markdown files to pdf / epub format☆12Oct 6, 2019Updated 6 years ago
- Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200☆124Feb 28, 2026Updated 7 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☆80Mar 18, 2026Updated 6 months ago
- An unofficial implementation of MemTree: From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs☆18Jul 14, 2025Updated last year
- A PyTorch native library for training speculative decoding models☆253Updated this week