b9828
opencl: flash attention improvement (#25069) opencl: rework FA kernel for f16 and f32 opencl: flash-attention prefill prepass kernels flash_attn_kv_pad_f16 pads the tail KV tile to a…
Infrastructure 949 stories
b9827
[CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy (#25057) [CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy Add a CUDA ggml_cpy fast path for same-type, same-shape…
b9826
sycl : fix failed ut cases of norm (#25044) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…
b9825
vulkan: fix step operator for 0 input (#25036) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…
b9824
binaries : Improve rpc-server and export-graph-ops names. (#25045) Tests are generally prefixed with -test, so rename export-graph-ops accordingly. rpc-server is probably too generic a name for…
b9823
ci : add windows-openvino to check-release (#25022) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu…
b9822
tests : fix test-chat-template --no-common option (#25075) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu…
b9821
app : allow --version, --licenses & --help (#25054) Signed-off-by: Adrien Gallouët angt@huggingface.co macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel…
Track total merges by adoption phase in enterprise and organization reports
Building on the AI adoption phase cohorts added to the Copilot usage metrics API, organization and enterprise reports now report the total number of pull requests…
Deploy a Production-Ready NVIDIA AI-Q Blueprint on Oracle Cloud Infrastructure
AI agents have changed a lot in the last two years. The first could only answer one question at a time. Then came multi-turn chat, where…
b9820
sched : reintroduce less synchronizations during split compute (#20793) CUDA: Improve performance via less synchronizations between token (#17795) Adds CPU-to-CUDA copy capability to ggml_backend_cuda_cpy_tensor_async() Adds function…
b9817
openvino: Update to OV 2026.2.1, self-contained release packages, operator improvements (#24974) Update to OV 2026.2.1, Make OV release packages self-contained Update to OV 2026.2.1, Make OV…
b9816
sync : ggml macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64…
MAI-Code-1-Flash for Copilot Business and Copilot Enterprise
MAI-Code-1-Flash, Microsoft AI’s in-house coding model, is now generally available for GitHub Copilot Business and Copilot Enterprise, building on its recent expansion across Copilot surfaces. Purpose-built…
b9814
vulkan: opt mul_mat_vecq for mi50 (#22933) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64…
Creating the NVIDIA Nemotron 3 Ultra NVFP4 Checkpoint with NVIDIA Model Optimizer
As context windows grow longer, moving large model weights efficiently becomes critical to performance. A common way to address this is quantization, an...
b9813
vulkan: add INTEL_XE1 arch enum and enable coopmat1 on Intel Xe-LPG Plus (#24404) vulkan: add INTEL_PRE_XE2 arch enum and enable coopmat1 on Intel Xe-LPG Plus (1/3,…
b9811
vulkan: Workaround compiler bug in conv2d coopmat2 path (#24924) vulkan: Workaround compiler bug in conv2d coopmat2 path apply same workaround to CONV_3D Apply suggestion from @jeffbolznv…
b9810
CUDA: add cublasSgemmBatched mapping for HIP/MUSA vendor headers (#25033) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…
b9804
mamba2: remove hardcoded 2x expansion factor and invalid d_inner % d_state check (#23082) mamba2: remove hardcoded 2x expansion factor, support any expand value mamba2: remove invalid…
b9803
opencl: flush profiling batch at shutdown for incomplete batches (#25016) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…
b9802
macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x…
Streamlining Resource Binding with End-to-End Support for Vulkan Descriptor Heaps
Shaders are GPU programs that process visual data—such as rays, pixels, geometry, and textures—to produce specific rendering effects. Shaders find necessary...
Copilot code review: Analysis depth and efficiency updates
Copilot code review now uses the built-in file exploration tools available in the Copilot CLI and SDK, significantly improving review cost efficiency with no change to…