A collection of tricks and tools to speed up transformer models
☆233Sep 24, 2026Updated 2 weeks ago
Alternatives and similar repositories for transformer-tricks
Users that are interested in transformer-tricks are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality…☆52Mar 25, 2025Updated last year
- DUTH RISC-V Microprocessor☆26Apr 5, 2026Updated 6 months ago
- Code repository for ICLR 2025 paper "LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid"☆28Mar 2, 2025Updated last year
- ☆138May 29, 2025Updated last year
- Official implementation for "K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling"☆19Aug 16, 2026Updated last month
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Fast Floating Point Operators for High Level Synthesis☆26Feb 23, 2023Updated 3 years ago
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 9 months ago
- Official PyTorch implementation of "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" (ICML 2025)☆58Apr 13, 2026Updated 5 months ago
- ☆12Updated this week
- ☆92Jan 23, 2025Updated last year
- Implementation of Deep Learning Models in JAX (equinox)☆25Sep 24, 2026Updated 2 weeks ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆33Mar 30, 2025Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆284Jul 6, 2025Updated last year
- ☆69Mar 21, 2025Updated last year
- 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.
- supporting pytorch FSDP for optimizers☆85Dec 8, 2024Updated last year
- ☆126May 28, 2024Updated 2 years ago
- Systolic Three Matrix Multiplier for Graph Convolutional Networks using High Level Synthesis☆24Jul 29, 2022Updated 4 years ago
- ☆93Jul 7, 2025Updated last year
- Auto Thinking Mode switch for Qwen3 in Open webui☆70May 8, 2025Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆172Oct 13, 2025Updated 11 months ago
- Try out HallOumi, a state-of-the-art claim verification model in a simple UI!☆41Sep 14, 2026Updated 3 weeks ago
- The Quasi Quantum Assembly Programming Language☆36Nov 14, 2025Updated 10 months ago
- Helpful tools and examples for working with flex-attention☆1,257Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design☆26May 29, 2025Updated last year
- ☆14Dec 22, 2024Updated last year
- ☆288Jun 6, 2025Updated last year
- BFloat16 Fused Adam Operator for PyTorch☆20Nov 16, 2024Updated last year
- LLM KV cache compression made easy☆1,224Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,841Updated this week
- A toolkit for scaling law research ⚖☆69Jan 27, 2025Updated last year
- This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.☆18Mar 31, 2026Updated 6 months ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆214Dec 4, 2025Updated 10 months ago
- This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the …☆54Dec 23, 2024Updated last year
- Implementation and evaluation of Scaling Embedding Layers in Language Models research paper☆17Feb 2, 2026Updated 8 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Jun 21, 2023Updated 3 years ago
- AirLLM 70B inference with single 4GB GPU☆21Jun 27, 2025Updated last year
- Muon is Scalable for LLM Training☆1,548Aug 3, 2025Updated last year
- Public Goods Game (PGG) Benchmark: Contribute & Punish is a multi-agent benchmark that tests cooperative and self-interested strategies a…☆42Apr 10, 2025Updated last year