RT @DAlistarh: Announcing our early work on FP4 inference for LLMs! .- QuTLASS: low-precision kernel support for Blackwell GPUs.- FP-Quant:….

RT @DAlistarh: We are introducing Quartet, a fully FP4-native training method for Large Language Models, achieving optimal accuracy-efficie….

RT @DAlistarh: Introducing MoE-Quant, a fast version of GPTQ for MoEs, with:.* Optimized Triton kernels and expert&data parallelism.* Quant….

RT @DAlistarh: Our QuEST paper was selected for Oral Presentation at ICLR @sparseLLMs workshop! .QuEST is the first algorithm with Pareto-o….

RT @spcl_eth: Yesterday, Jiale and Roberto presented the paper MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language….

RT @rush_tabesh: Happy to introduce #HALO lower-precision fine-tuning for LLMs. With proper Hadamard transforms, #HALO enables accurate INT….

RT @AshkboosSaleh: Happy to release #HALO, a Hadamard-Assisted Lower-Precision scheme that enables INT8/FP6 full #finetuning (FFT) of LLMs.….

RT @RedHat: Today, Red Hat completed the acquisition of @NeuralMagic, a pioneer in software and algorithms that accelerate #GenAI inference….

RT @_EldarKurtic: 4) The 2:4 models are compatible with quantization. We apply GPTQ to quantize weights to 4-bit integers, but modify it su….

RT @_EldarKurtic: 2:4 Sparsity + @AIatMeta Llama-3.1: At @neuralmagic, we've developed a recipe to produce very competitive sparse LLMs, a….

RT @neuralmagic: Sparse-Marlin is here and integrated into @vllm_project! This GPU-optimized kernel accelerates matrix multiplication with….

RT @neuralmagic: Code: Paper: Made possible by: @DAlistarh, @elias_frantar, @RobertoL_Cas….

RT @DAlistarh: Happy to release the write-up on the MARLIN kernel for fast LLM inference, now supporting 2:4 sparsity! .Led by @elias_fran….

RT @BiblioInf_UDC: 📰Xa dispoñible no #RUC e #Zenodo o traballo do grupo #GAC da @FIC_UDC: "STuning-DL: Model-Driven Autotuning of Sparse GP….

RT @thoefler: Is @nvidia's 2:4 sparsity not enough for your ambitions with #AI models? Then check out Roberto's structured sparse extension….

RT @spcl_eth: Don't miss Roberto's talk at #SC23 tomorrow at 11:30AM as he unveils VENOM - a new sparse matrix format enabling arbitrary N:….

Join us at #SC23 on Nov 16 at 11:30AM as we unveil VENOM - a new sparse matrix format enabling arbitrary N:M patterns on Sparse Tensor Cores, natively restricted to 2:4. Plus, explore Spatha 🗡️, our sparse library for VENOM achieving up to 37x over SOTA dense methods.

RT @spcl_eth: Join Roberto at #SC23 on Nov 16 at 11:30AM as he unveils VENOM - a new sparse matrix format enabling arbitrary N:M patterns o….

RT @docmilanfar: Sparsity people trying to publish in ML conferences

RT @AiBreakfast: 🤯 Full body tracking now possible using only WiFi signals. A deep neural network maps the phase and amplitude of WiFi sign….