Copertina

MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zou, Jiaxiang, Chen, Yonghao, Wu, Ruilong, Chen, Xinyu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Hardware Architecture
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Diagnosing FP4 inference: a layer-wise and block-wise sensitivity analysis of NVFP4 and MXFP4
di: Cim, Musa, et al.
Pubblicazione: (2026)

FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables
di: Park, Gunho, et al.
Pubblicazione: (2025)

DGEMM without FP64 Arithmetic - Using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme
di: Mukunoki, Daichi
Pubblicazione: (2025)

Faster Inference of LLMs using FP8 on the Intel Gaudi
di: Lee, Joonhyung, et al.
Pubblicazione: (2025)

LLM-FP4: 4-Bit Floating-Point Quantized Transformers
di: Liu, Shih-yang, et al.
Pubblicazione: (2023)

TMA-Adaptive FP8 Grouped GEMM: Eliminating Padding Requirements in Low-Precision Training and Inference on Hopper
di: Su, Zhongling, et al.
Pubblicazione: (2025)

Hardware-Efficient CNNs: Interleaved Approximate FP32 Multipliers for Kernel Computation
di: Gowda, Bindu G, et al.
Pubblicazione: (2025)

FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
di: Xia, Haojun, et al.
Pubblicazione: (2024)

Balancing FP8 Computation Accuracy and Efficiency on Digital CIM via Shift-Aware On-the-fly Aligned-Mantissa Bitwidth Prediction
di: Zhao, Liang, et al.
Pubblicazione: (2026)

Schrödinger's FP: Dynamic Adaptation of Floating-Point Containers for Deep Learning Training
di: Nikolić, Miloš, et al.
Pubblicazione: (2022)

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
di: Zhang, Jintao, et al.
Pubblicazione: (2025)

Affordable HPC: Leveraging Small Clusters for Big Data and Graph Computing
di: Wu, Ruilong, et al.
Pubblicazione: (2024)

Enhanced LPDDR4X PHY in 12 nm FinFET
di: Feldmann, Johannes, et al.
Pubblicazione: (2025)

Mixed Structural Choice Operator: Enhancing Technology Mapping with Heterogeneous Representations
di: Hu, Zhang, et al.
Pubblicazione: (2025)

Execution-Centric Characterization of FP8 Matrix Cores, Asynchronous Execution, and Structured Sparsity on AMD MI300A
di: Jarmusch, Aaron, et al.
Pubblicazione: (2026)

COMET: Towards Partical W4A4KV4 LLMs Serving
di: Liu, Lian, et al.
Pubblicazione: (2024)

Corrigendum to: A Systematic Study of DDR4 DRAM Faults in the Field
di: Beigi, Majed Valad, et al.
Pubblicazione: (2024)

31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding
di: Dong, Pingcheng, et al.
Pubblicazione: (2026)

TensorPool: A 3D-Stacked 8.4TFLOPS/4.3W Many-Core Domain-Specific Processor for AI-Native Radio Access Networks
di: Bertuletti, Marco, et al.
Pubblicazione: (2026)

DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale
di: Zheng, Ziyang, et al.
Pubblicazione: (2025)

$R^4$: A Racetrack Register File with Runtime Software Reconfiguration
di: Hakert, Christian, et al.
Pubblicazione: (2025)

Iterative LLM-Based Assertion Generation Using Syntax-Semantic Representations for Functional Coverage-Guided Verification
di: Wang, Yonghao, et al.
Pubblicazione: (2026)

Towards Reliable Systems: A Scalable Approach to AXI4 Transaction Monitoring
di: Liang, Chaoqun, et al.
Pubblicazione: (2025)

Hardware-Efficient Accurate 4-bit Multiplier for Xilinx 7 Series FPGAs
di: Kida, Misaki, et al.
Pubblicazione: (2025)

Block-SSD: A New Block-Based Blocking SSD Architecture
di: Wong, Ryan, et al.
Pubblicazione: (2024)

A Benchmarking Platform for DDR4 Memory Performance in Data-Center-Class FPGAs
di: Galimberti, Andrea, et al.
Pubblicazione: (2025)

A High-Throughput Hardware Accelerator for Lempel-Ziv 4 Compression Algorithm
di: Chen, Tao, et al.
Pubblicazione: (2024)

CoverAssert: Iterative LLM Assertion Generation Driven by Functional Coverage via Syntax-Semantic Representations
di: Wang, Yonghao, et al.
Pubblicazione: (2026)

Evaluation of GPU Video Encoder for Low-Latency Real-Time 4K UHD Encoding
di: Arunruangsirilert, Kasidis, et al.
Pubblicazione: (2025)

EA4RCA:Efficient AIE accelerator design framework for Regular Communication-Avoiding Algorithm
di: Zhang, W. B., et al.
Pubblicazione: (2024)

A4: Microarchitecture-Aware LLC Management for Datacenter Servers with Emerging I/O Devices
di: Park, Haneul, et al.
Pubblicazione: (2025)

DAE4HLS: Exposing Memory-Level Parallelism for High-Level Synthesis using Explicit Decoupling
di: Metz, David, et al.
Pubblicazione: (2026)

Kratos: An FPGA Benchmark for Unrolled DNNs with Fine-Grained Sparsity and Mixed Precision
di: Dai, Xilai, et al.
Pubblicazione: (2024)

PIMSIM-NN: An ISA-based Simulation Framework for Processing-in-Memory Accelerators
di: Wang, Xinyu, et al.
Pubblicazione: (2024)

4T2R X-ReRAM CiM Array for Variation-tolerant, Low-power, Massively Parallel MAC Operation
di: Kihara, Fuyuki, et al.
Pubblicazione: (2025)

Think with Self-Decoupling and Self-Verification: Automated RTL Design with Backtrack-ToT
di: Chao, Zhiteng, et al.
Pubblicazione: (2025)

AssertMiner: Module-Level Spec Generation and Assertion Mining using Static Analysis Guided LLMs
di: Lyu, Hongqin, et al.
Pubblicazione: (2025)

DeepAssert: An LLM-Aided Verification Framework with Fine-Grained Assertion Generation for Modules with Extracted Module Specifications
di: Wang, Yonghao, et al.
Pubblicazione: (2025)

AssertFix: Empowering Automated Assertion Fix via Large Language Models
di: Lyu, Hongqin, et al.
Pubblicazione: (2025)

RidgeWalker: Perfectly Pipelined Graph Random Walks on FPGAs
di: Tan, Hongshi, et al.
Pubblicazione: (2026)