b10105
args: refactor mlock/mmap/directio into load-mode (#20834) args: overhaul mmap/mlock/dio into single arg Signed-off-by: Aaron Teo aaron.teo1@ibm.com docs: update docs with llama-gen-docs Signed-off-by: Aaron Teo aaron.teo1@ibm.com chore:…
Infrastructure 944 stories
At AI Summit, South Korea Outlines Its AI Future With NVIDIA and Partners
At this week’s AI Summit in San Francisco, South Korean President Jae Myung Lee and some of the country’s top business leaders and researchers are meeting…
b10108
hexagon: further improved pipeline of the core bits (L2, DMA, MM, FA)…
Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding
We ran 452 DeepSWE rollouts on Kimi K3 and Claude Fable 5. Fable leads pass@1 by 1.4 points; Kimi K3 wins pass@4 and delivers 2.8x the…
b10099
CUDA: Improve NVFP4 W4A4 activation quantization (#25730) Squash history before conflict-resolution during rebase on master WIP commit Add 32-byte loads, restore per-block amax Use nvfp4x4 intrinsic…
Copilot cloud agent for Linear is now generally available
You can now assign issues in Linear to Copilot cloud agent, our asynchronous, autonomous background agent. When you assign a Linear issue to Copilot, it will:…
GitHub MCP Server supports the next MCP specification
The MCP protocol is going stateless on 28th July 2026, and the GitHub MCP Server supports the latest spec ahead of the official release. What’s changing…
b10098
hexagon: activation ops update (#25974) hex-geglu: optimized all-in-one geglu microkernel hex-geglu: enable non-contiguous src and strided DMA hex-act: enable non-contiguous srs and strided DMA for rest…
b10094
common: infer the speculative type from the draft repo sidecars (#25989) With -hfd pointing to a repo that ships mtp-/dflash-/eagle3- sidecars and no --spec-type given, the…
b10093
Fix DeepSeek4 crafted template (#25414) chat: fix DS4 template to explicitly follow reference behavior Support DeepSeekv4 flag (drop_reasoning). fix: hook DS3.2 parser for DS4 as well…
Debugging Ray Tracing Applications Using NVIDIA OptiX Toolkit
NVIDIA OptiX ray tracing engine is an application framework for achieving optimal ray tracing performance on the GPU. Applications using OptiX can fail in ways...
Start Customizing NVIDIA Nemotron 3 Nano with Prime Intellect Lab in Minutes
Customization is what enables developers to take a general model and tailor it to use cases, domains, languages, and more. However, customization comes with a...
Agent automation controls in GitHub Issues in public preview
Agent automations increasingly label, type, assign, and close issues for you. GitHub Issues now shows the reason behind each change and lets you review them before…
GeForce NOW Sets Sail With ‘Path of Exile: Curse of the Allflame’ Joining the Cloud
Lock in and load up the cloud. GFN Thursday brings fresh updates and new adventures, all ready to play without waiting for downloads. Set sail in…
b10092
ggml: enable PowerPC backend variants on AIX (#25983) ggml: enable PowerPC backend variants on AIX Allow the PowerPC CPU backend variants to be built on AIX…
b10103
metal : add f16 type support to leaky relu (#25981)
NVIDIA AI Supercomputer Comes Online at Naval Postgraduate School
NVIDIA founder and CEO Jensen Huang today visited the Naval Postgraduate School in Monterey, California, to commission an NVIDIA DGX GB300 system — bringing one of…
The production platform for open-weight AI inference
Run open models in production with full control over performance, cost, and quality. Deploy in minutes, roll out safely, and scale to your SLOs.
b10091
ci : fix SYCL package shared library lookup (#25987) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b10090
webgpu : add CONV_2D_DW (depthwise conv2d) kernel (#25847) webgpu : add CONV_2D_DW (depthwise conv2d) kernel Implement GGML_OP_CONV_2D_DW for the WebGPU backend, ported from the Vulkan backend's…
b10089
cuda: GET_ROWS quants (#25962) cuda: add k-quant support to GET_ROWS Device-side embedding lookups require GET_ROWS to handle the k-quants used by common GGUF recipes (Q4_K_M stores…
Make Long-Running NVIDIA TensorRT Engine Builds Observable and Cancelable in Python or C++
A TensorRT engine build can take seconds to many minutes. Large strongly typed models, deep tactic search, and a cold timing cache on a brand-new GPU…
New Copilot usage metrics impact dashboard
We’ve released a new Copilot metrics impact dashboard for enterprise administrators and organization owners. This dashboard helps you tell a deeper Copilot impact story by sharing…
NVIDIA Open Sources First GPU-Accelerated Medical Physics Simulation Framework
Before a healthcare robot can be useful in the real world, it has to learn how the physical world pushes back. Anatomy varies. Instruments bend, press,…