No article text was recorded for this version.
fused quantization kernels
Version 1 of 147 papers52 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment
- Blog: QPyTorch: A Low-Precision Arithmetic Simulation Framework
- Blog: QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models
- Blog: VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
- Blog: FBQuant: FeedBack Quantization for Large Language Models
- Blog: SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
- Blog: TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly
- Blog: ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
- Blog: EQuARX: Efficient Quantized AllReduce in XLA for Distributed Machine Learning Acceleration
- Blog: KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- Blog: AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
- Blog: Training Transformers with 4-bit Integers
- Blog: FlashOptim: Optimizers for Memory-Efficient Training
- Blog: FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
- Blog: A co-design method of customized ISA design space exploration and fixed-point library construction for RISC-V dedicated processor
- Blog: ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
- Blog: Scaling On-Device GPU Inference for Large Generative Models
- Blog: RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
- Blog: SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
- Blog: EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
- Blog: KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
- Blog: LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving
- Blog: BASS: Batched Attention-optimized Speculative Sampling
- Blog: STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control
- Blog: Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
- Blog: GPTQT: Quantize Large Language Models Twice to Push the Efficiency
- Blog: QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
- Blog: Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference
- Blog: Quartet: Native FP4 Training Can Be Optimal for Large Language Models
- Blog: ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
- Blog: MBQ: Modality-Balanced Quantization for Large Vision-Language Models
- Blog: QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices
- Blog: FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs
- Blog: Collage: Light-Weight Low-Precision Strategy for LLM Training
- Blog: KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
- Blog: Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases
- Blog: QPP: Real-Time Quantization Parameter Prediction for Deep Neural Networks
- Blog: FlatQuant: Flatness Matters for LLM Quantization
- Blog: Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression
- Blog: MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models
- Blog: PacQ: A SIMT Microarchitecture for Efficient Dataflow in Hyper-asymmetric GEMMs
- Blog: Quamba: A Post-Training Quantization Recipe for Selective State Space Models
- Blog: Modality-Aware Block Rotation for Vision-Language-Action Model Quantization
- Blog: COMET: Towards Practical W4A4KV4 LLMs Serving
- Blog: WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
- Blog: TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
- Blog: SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
History & citation
Current · Permanent link
- This direction split from Fused Kernels for Quantized Execution in Large Models (79% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_fused_quantization_kernels_d6efe14a,
title = {fused quantization kernels},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/fused-quantization-kernels/rdr_d6efe14a7e3540cfbec365cecb0b9062},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_fused_quantization_kernels_d6efe14a_v1,
title = {fused quantization kernels},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/fused-quantization-kernels/rdr_d6efe14a7e3540cfbec365cecb0b9062/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}