Implementation for IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).
☆25Jun 9, 2026Updated last month
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:
- Load and run Llama from safetensors files in C☆15Oct 24, 2024Updated last year
- ☆11Nov 22, 2025Updated 8 months ago
- Accelerate multihead attention transformer model using HLS for FPGA☆13Dec 7, 2023Updated 2 years ago
- 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
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆13Apr 17, 2025Updated last year
- ☆15Mar 22, 2024Updated 2 years ago
- ☆13Jan 7, 2025Updated last year
- SGEMM optimization with cuda step by step☆23Mar 23, 2024Updated 2 years ago
- ☆76Mar 26, 2025Updated last year
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated 11 months ago
- Running inference on the ZeroSCROLLS benchmark☆22Apr 18, 2024Updated 2 years ago
- ☆12Mar 21, 2024Updated 2 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.
- Whisper in TensorRT-LLM☆17Sep 21, 2023Updated 2 years ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆54Mar 27, 2024Updated 2 years ago
- Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"☆15Mar 6, 2025Updated last year
- Loop Nest - Linear algebra compiler and code generator.☆20Oct 22, 2022Updated 3 years ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆17Jul 17, 2026Updated last week
- ☆326Jul 10, 2025Updated last year
- ☆16Mar 13, 2023Updated 3 years ago
- An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences☆32Mar 7, 2024Updated 2 years ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆130Jul 4, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Official repository of "Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions", ICLR 2024 Sp…☆21Mar 7, 2024Updated 2 years ago
- ⚡️Qwen-Image 4.8x🎉 speedup with Hybrid Acceleration for low VRAM GPUs☆17Oct 24, 2025Updated 9 months ago
- The source code and dataset mentioned in the paper Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmar…☆57Nov 5, 2024Updated last year
- 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
- Standalone Flash Attention v2 kernel without libtorch dependency☆113Sep 10, 2024Updated last year
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆47Feb 28, 2026Updated 4 months 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☆82Aug 12, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆35Dec 22, 2025Updated 7 months ago
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆46May 23, 2023Updated 3 years ago
- ☆80Apr 22, 2025Updated last year
- Python script for controlling the debug-jtag port of riscv cores☆15Mar 27, 2021Updated 5 years ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆47Jun 11, 2025Updated last year
- [NAACL 2025] MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning☆21May 31, 2025Updated last year
- Optimizing the Deployment of Tiny Transformers on Low-Power MCUs☆38Sep 2, 2024Updated last year