GEMM
PulseAugur coverage of GEMM — every cluster mentioning GEMM across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New tools and research tackle GPU optimization for AI workloads
Several research papers and a new open-source tool address challenges in optimizing AI workloads on GPUs. COMPASS-ABS aims to reduce fragmentation in shared GPU clusters for deep learning training, improving resource ut…
-
AI alignment advocates call for regulation of GEMM and GEMV operations
A call has been made to regulate GEMM and GEMV operations, which are fundamental to AI alignment and model execution. The proposal suggests that entities utilizing BLAS (Basic Linear Algebra Subprograms) without proper …
-
Together AI optimizes ThunderKittens for NVIDIA Vera Rubin Blackwell GPUs
Together AI has gained access to NVIDIA's Vera Rubin NVL72 platform, which is based on the Blackwell architecture. Their team has updated their ThunderKittens software to leverage new features of the Vera Rubin chip, sp…
-
New im2win convolution method boosts GPU performance and memory efficiency
Researchers have developed an enhanced version of the im2win convolution method, designed for greater memory efficiency and performance on GPUs. This updated method supports full precision on CUDA cores and half precisi…
-
Hand-written PTX kernels show significant speedups for INT8/INT4 GEMM on NVIDIA L4 GPUs
A new research paper explores the performance benefits of using hand-written PTX (Parallel Thread Execution) kernels for GEMM (General Matrix Multiply) operations on NVIDIA L4 GPUs, compared to the standard WMMA (Warp M…
-
InstantSfM offers GPU-native structure-from-motion for deep learning era
Researchers have developed InstantSfM, a novel GPU-native structure-from-motion system designed to integrate seamlessly with deep learning pipelines. This system addresses the limitations of traditional CPU-centric SfM …
-
MiniCPM-V 4.6 multimodal assistant runs on 2011 GPU
Researchers have successfully deployed the MiniCPM-V 4.6 multimodal assistant on a 2011 NVIDIA Tesla C2075 GPU, which has 6GB of memory. This involved creating an all-GPU inference engine optimized for the older Fermi a…
-
ExaGEMM framework boosts CPU ML inference with low-bit GEMM optimization
Researchers have developed ExaGEMM, a framework designed to optimize low-bit General Matrix Multiply (GEMM) operations for machine learning inference on CPUs. This framework addresses the challenge of efficiently execut…
-
ExaGEMM framework boosts CPU ML inference with low-bit GEMM optimization · 2 sources tracked
Researchers have developed ExaGEMM, a framework designed to optimize low-bit General Matrix Multiply (GEMM) operations for machine learning inference on conventional CPUs. This framework addresses the challenge of effic…
-
New paper coins "baseline capture" to describe innovation roadblocks
A new paper introduces the concept of "baseline capture," a phenomenon where an incumbent system's output becomes the de facto specification for evaluating new computational reformulations. This can hinder innovation by…
-
New kernels boost LLM inference speed by fusing SwiGLU activations
Researchers have developed new techniques to accelerate the inference of large language models (LLMs) by fusing SwiGLU activation functions directly into GEMM operations at the tile level. These methods, implemented usi…
-
New book details modern GPU programming for AI workloads
A new book titled "Modern GPU Programming for MLSys" aims to demystify high-performance GPU kernel development for machine learning systems. The book, originating from Carnegie Mellon University's Machine Learning Syste…
-
Apple M4 Max GPU's Tensor Compute Path Emulated, Not Accelerated
Researchers have reverse-engineered the Metal 4.1 tensor compute path on Apple's M4 Max GPU, revealing that the fp8 matmul2d operation is emulated rather than hardware-accelerated. This means the operation runs on the G…
-
New framework enhances LLM-generated Verilog with feedback and skill evolution
Researchers have developed Verilog-Evolve, a novel framework designed to enhance the generation of Verilog code using large language models. This system moves beyond isolated sampling and functional checking by incorpor…
-
TileLang simplifies GPU kernel writing with Python interface
A new programming language called TileLang aims to simplify GPU kernel development by offering a middle ground between high-level frameworks like Triton and low-level control like CUTLASS. TileLang allows developers to …
-
Sakana AI, NVIDIA unveil TwELL for faster LLM training and inference
Researchers from Sakana AI and NVIDIA have developed TwELL, a novel method that significantly speeds up large language model (LLM) operations. By targeting the feedforward layers, which are computationally intensive, Tw…
-
Tempus framework offers scalable, resource-efficient GEMM for edge AI
Researchers have developed Tempus, a new framework designed to optimize General Matrix Multiplication (GEMM) for edge AI deployments on AMD Versal SoCs. Unlike existing spatial scaling methods that fail on resource-cons…