[FPGA'26 Best Paper Nomination] CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving
☆42Aug 7, 2026Updated 2 months ago
Alternatives and similar repositories for CXL-SpecKV
Users that are interested in CXL-SpecKV are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Collection for Distributed Reinforcement Learning Papers☆18Sep 24, 2025Updated last year
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆53Aug 2, 2026Updated 2 months ago
- PiKV: KV Cache Management System for Mixture of Experts [Efficient ML System]☆66Oct 21, 2026Updated last week
- TeLLMe: An Efficient End-to-End Ternary LLM Prefill and Decode Accelerator with Table-Lookup Matmul on Edge FPGAs [FPGA2026]☆40Mar 11, 2026Updated 7 months ago
- Collection of kernel accelerators optimised for LLM execution☆35Feb 26, 2026Updated 8 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A Serving System for Distributed and Parallel LLM Quantization [Efficient ML System]☆26Jun 18, 2025Updated last year
- ☆50Apr 5, 2026Updated 6 months ago
- DFVG: A Heterogeneous Architecture for Speculative Decoding with Draft-on-FPGA and Verify-on-GPU.☆29Nov 26, 2025Updated 11 months ago
- ☆103Jun 25, 2026Updated 4 months ago
- ☆83Feb 4, 2021Updated 5 years ago
- [DATE'25, ICCAD'25] An embedded FPGA-based LLM accelerator capable of supporting Llama2-7B☆222Jul 30, 2026Updated 3 months ago
- Adaptive Topology Reconstruction for Robust Graph Representation Learning [Efficient ML Model]☆10Feb 11, 2025Updated last year
- CXL Memory Resource Kit top-level repository☆65Oct 31, 2022Updated 4 years ago
- PCCX v002 KV260 board/model integration and verification, consuming a pinned reusable core. Operated by Altifigence.☆21Sep 27, 2026Updated last month
- 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.
- RapidLayout: Fast Hard Block Placement of FPGA-Optimized Systolic Arrays using Evolutionary Algorithms☆20Sep 15, 2026Updated last month
- A full-system, cycle-level simulator based on gem5 that provides complete support for all three CXL sub-protocols and all three types of …☆173May 11, 2026Updated 5 months ago
- Accelerating Multitask Training Trough Adaptive Transition [Efficient ML Model]☆12May 23, 2025Updated last year
- Reconfigurable Stream Network Architecture☆18Aug 13, 2026Updated 2 months ago
- ☆119Jun 9, 2023Updated 3 years ago
- Artifact for Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization☆20May 9, 2025Updated last year
- A comprehensive repository for Compute Express Link (CXL) resources: covering research papers, specifications, simulation/emulation tools…☆31Feb 24, 2026Updated 8 months ago
- FPGA-based SATA-DMA Host Controller☆36Nov 20, 2025Updated 11 months ago
- Days: a Performant Discrete-Event Simulator for Network Simulations☆17Oct 14, 2026Updated 2 weeks ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Board files to build the ZCU111 PYNQ image☆22Oct 11, 2022Updated 4 years ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆55Oct 18, 2024Updated 2 years ago
- Source code for "Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference." In NeurIPS 2024☆22Dec 1, 2024Updated last year
- ☆293Oct 24, 2025Updated last year
- Systematic CXL Memory Characterization and Performance Analysis at Scale (ASPLOS'25)☆26Aug 27, 2026Updated 2 months ago
- tmp DPI☆14Dec 18, 2024Updated last year
- AVPipe :-)☆12Jul 16, 2021Updated 5 years ago
- ☆15Jun 10, 2026Updated 4 months ago
- ☆27Jan 22, 2023Updated 3 years ago
- 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.
- nn2FPGA converts ONNX models into FPGA dataflow accelerators with seamless ONNX Runtime integration.☆25Updated this week
- XtraMAC code repo (Accepted by ISCA2026)☆32Sep 9, 2026Updated last month
- Autonomous driving of a drone and object classification through camera with yolo detection.A project that provides an adaptive PID contro…☆11Sep 30, 2025Updated last year
- Allo Accelerator Design and Programming Framework (PLDI'24)☆414Oct 12, 2026Updated 2 weeks ago
- This is simply a binary neural network implemented on FPGA. The one and only functionality of this crap is to recognize handwritten digit…☆12Apr 20, 2021Updated 5 years ago
- An open platform for exploring scale-up network systems.☆23Mar 16, 2026Updated 7 months ago
- AmorphOS open source FPGA operating system project☆10Apr 16, 2020Updated 6 years ago