hexagon
PulseAugur coverage of hexagon — every cluster mentioning hexagon across labs, papers, and developer communities, ranked by signal.
- 2026-10-09 product_launch Hexagon is deploying 1,000 humanoid robots into Schaeffler factories. source
11 day(s) with sentiment data
-
llama.cpp optimizes hexagon architecture with fused RMS_NORM operations
The llama.cpp project has released version b12181, which includes optimizations for the hexagon architecture. These changes focus on fusing post-norm residual additions into the RMS_NORM_MUL operation and refactoring RM…
-
llama.cpp b12030 fixes hexagon DMA transfer issues across platforms
The llama.cpp project has released version b12030, which includes a fix for DMA transfers on the hexagon architecture when strides exceed 24 bits. This issue could lead to truncated strides and incorrect addresses for l…
-
llama.cpp project releases multiple pre-release updates with performance improvements
The llama.cpp project has released several pre-release versions, including b12121, b12119, b12118, b12116, b12114, b12110, b12109, b12102, b12100, and b12109. These updates address various issues and introduce new featu…
-
llama.cpp adds UPSCALE support to hexagon backend
The llama.cpp project has released version b11982, introducing support for the UPSCALE operation within its hexagon backend. This update includes optimizations for nearest and bilinear upscaling, improved handling of no…
-
llama.cpp b11970 adds Hexagon conv2d support across platforms
The llama.cpp project has released version b11970, which includes significant enhancements to its Hexagon backend, specifically adding support for the conv2d operation. This update refactors the conv2d kernel parameters…
-
llama.cpp b11909 release optimizes MUL_MAT_ID operations
The llama.cpp project has released version b11909, introducing optimizations for the MUL_MAT_ID operation on various platforms. These improvements include vectorized zeroing and the removal of scalar division for the he…
-
llama.cpp releases optimizations, new ops; contrastive learning research published
The llama.cpp project has released two pre-release versions, b11936 and b11840, introducing optimizations and new operations. Version b11936 focuses on improving the k-pool sparse selection for models like Qwen4Exp and …
-
AI developments span model compression, code optimization, and talent investment
The llama.cpp project has released version b11875, which includes enhancements to its hexagon tools for collapsing and reshaping operations across various platforms like macOS, Linux, and Windows. Separately, a research…
-
llama.cpp b11868 optimizes flash attention; OCR code shows 10x slower performance on Intel
The llama.cpp project has released version b11868, introducing optimizations for multicore processing and flash attention, particularly for the Gemma 4 model on Apple Silicon hardware. This release includes a new flag, …
-
llama.cpp adds Q1_0 and Q2_0 quantization support for Hexagon backend
The llama.cpp project has released an update, b11716, which introduces support for Q1_0 and Q2_0 quantization formats. This update includes optimizations for the hexagon backend, specifically enhancing the HMX MUL_MAT p…
-
llama.cpp project releases pre-updates with OS and model optimizations
The llama.cpp project has released several pre-release updates, including b11732 which fixes a CUDA warning and adds support for various operating systems like macOS, iOS, Linux, Android, Windows, and OpenEuler. Release…
-
New math repository Hexagon launches to host AI-generated content
A new open-access repository for mathematics, named Hexagon, has been launched to specifically accommodate AI-generated content. This initiative addresses the refusal of existing platforms like arXiv to host such materi…
-
llama.cpp releases pre-updates with new features and optimizations
The llama.cpp project has released several pre-release updates, including b11675 which adds audio streaming capabilities and support for voxtral-realtime, and b11672 which refines the handling of image resolutions for l…
-
Hexagon deploys 1,000 humanoid robots in Schaeffler factories
Hexagon is deploying 1,000 humanoid robots into Schaeffler factories, marking a significant scale-up from an initial pilot program. The company's president, Arnaud Robert, discussed the challenges and strategies involve…
-
llama.cpp fixes Hexagon IM2COL DMA overflow bug
The llama.cpp project released version b11516, which addresses an Integer-to-Integer (IM2COL) patch-embed Direct Memory Access (DMA) ring overflow issue. This overflow occurred when the system attempted to queue more DM…
-
llama.cpp project releases b11434 with hexagon and ssm-conv updates
The llama.cpp project has released version b11434, which includes updates to its hexagon and ssm-conv components. These updates focus on improving the efficiency and structure of DMA operations for prefill and decode pr…
-
llama.cpp optimizes hexagon architecture for faster AI model inference
The llama.cpp project has released an update, b11430, focusing on performance improvements for the hexagon architecture. This update introduces head-parallel partitioning for flash-attention, allowing each core to proce…
-
llama.cpp project releases pre-release updates with performance optimizations
The llama.cpp project has released several pre-release updates, including improvements to GPU cache management for MoE experts, optimizations for various quantization types on Apple Silicon, and fixes for Metal fusion o…
-
llama.cpp releases b11347 with HTP skeleton updates
The llama.cpp project has released version b11347, which includes updates to its hexagon and HTP components. Specifically, the release focuses on installing rebuilt HTP skeleton files and fixing dependencies within the …
-
llama.cpp releases bring ZDNN backend, Vulkan tuning, and Hexagon support
The llama.cpp project has released several updates, including version b11269 which adds a ZDNN backend build and various CI improvements. Other recent releases focus on specific optimizations and bug fixes, such as impr…