Implementation for IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).
☆25Jun 9, 2026Updated 2 months ago
Alternatives and similar repositories for IceFormer
Users that are interested in IceFormer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Nov 22, 2025Updated 9 months ago
- Load and run Llama from safetensors files in C☆16Oct 24, 2024Updated last year
- 基于iOS直接调试ncnn源码，方便理解分析☆13Apr 8, 2019Updated 7 years ago
- Longitudinal Evaluation of LLMs via Data Compression☆32May 29, 2024Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- 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.
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆14Apr 17, 2025Updated last year
- ☆15Mar 22, 2024Updated 2 years ago
- SGEMM optimization with cuda step by step☆23Mar 23, 2024Updated 2 years ago
- ☆13Jan 7, 2025Updated last year
- ☆75Mar 26, 2025Updated last year
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated last year
- Running inference on the ZeroSCROLLS benchmark☆22Apr 18, 2024Updated 2 years ago
- ☆12Mar 21, 2024Updated 2 years ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆55Mar 27, 2024Updated 2 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.
- Loop Nest - Linear algebra compiler and code generator.☆20Oct 22, 2022Updated 3 years ago
- ☆32May 26, 2024Updated 2 years ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Jul 17, 2026Updated last month
- ☆333Jul 10, 2025Updated last year
- ☆16Mar 13, 2023Updated 3 years ago
- An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences☆33Mar 7, 2024Updated 2 years ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆132Jul 4, 2025Updated last year
- Beyond KV Caching: Shared Attention for Efficient LLMs☆20Jul 19, 2024Updated 2 years ago
- Implementation RefinedetLite☆29Dec 27, 2019Updated 6 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- This is the implementation that supports yolov5s, yolov5m, yolov5l, yolov5x.☆34Jun 22, 2022Updated 4 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Mar 7, 2024Updated 2 years ago
- Dumpy: A Compact and Adaptive Index for Large Data Series Collections (SIGMOD'23)☆13Dec 12, 2023Updated 2 years ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆113Sep 10, 2024Updated last year
- BH hackathon☆14Apr 4, 2024Updated 2 years ago
- KDD21 Deep Learning Embeddings for Data Series Similarity Search☆20Aug 5, 2021Updated 5 years ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆47Aug 22, 2026Updated 2 weeks ago
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆83Aug 12, 2024Updated 2 years ago
- 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.
- ☆35Dec 22, 2025Updated 8 months ago
- [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache☆43Jul 26, 2024Updated 2 years ago
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆46May 23, 2023Updated 3 years ago
- ☆89Apr 22, 2025Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆48Jun 11, 2025Updated last year
- Optimizing the Deployment of Tiny Transformers on Low-Power MCUs☆38Sep 2, 2024Updated 2 years ago
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆58Oct 27, 2025Updated 10 months ago