A user combined an RTX 5080 and RTX 3090 on an Asus Prime X570-Pro motherboard to run Qwen 3.6 27B Q8 at over 80 tokens per second. The setup required disabling CSM, enabling Above 4G Decoding and ReS…
Nvidia CEO Jensen Huang announced a paradigm shift in computing from data retrieval to real-time generation, driven by AI factories and purpose-built CPUs. The company's Vera CPU for agentic AI has al…
NVIDIA's Blackwell Ultra NVL72 platform achieved top performance on the first agentic AI benchmark, AgentPerf from Artificial Analysis, running up to 20 times more agents per megawatt than the previou…
NVIDIA's cuDF library now provides GPU-accelerated execution engines for the Polars Lazy API, enabling users to run dataframe operations on GPUs with automatic fallback to CPU when operations are unsu…
AMD released Lemonade SDK version 10.7, adding NVIDIA CUDA support to its local AI server solution that previously only supported AMD hardware, Apple Metal GPUs, and AArch64 CPUs. The update integrate…
A buyer who spent roughly $10,000 on both a Mac Studio M3 Ultra with 512 GB of unified memory and a dual NVIDIA DGX Spark setup ran the same 397-billion-parameter model on each machine and measured th…
Chris Lattner, a lead engineer on Apple's original OpenCL implementation, explains why OpenCL and other C++-based GPU programming models failed to become dominant in AI, citing slow committee-driven d…
A developer has published a guide for running Google's Gemma-4 12B instruction-tuned model on Windows Subsystem for Linux 2 (WSL2) using the llama.cpp framework. The process involves installing build …
NVIDIA released the Jetson Orin Nano Super Developer Kit for $249, offering up to 67 TOPS of AI performance for edge computing and robotics. The tiny dev board runs the full NVIDIA AI software stack a…
JAX defaults to loading data directly onto GPU memory when a CUDA-enabled version is installed, causing out-of-memory errors for large datasets that would fit in system RAM. The framework's `jax.devic…
A developer released a tool that allows Linux users to repurpose Nvidia GPU VRAM as swap space, effectively tripling addressable memory on systems with soldered RAM. The nbd-vram daemon uses CUDA's me…
NVIDIA Apex's FusedAdam optimizer and FusedLayerNorm normalization layers can accelerate Transformer training by up to 30% compared to standard PyTorch implementations, according to benchmark tests. T…
The CUDA caching allocator in PyTorch fragments memory when allocated blocks prevent adjacent free blocks from merging, causing allocation failures despite sufficient total free memory. This fragmenta…
PyTorch users can now implement custom operations in C++ and CUDA for use in both Python and C++ inference programs, with automatic device dispatch between CPU and CUDA implementations. The approach s…
Microsoft announced the Surface Laptop Ultra, a device built in partnership with NVIDIA and designed for creators, developers, and AI builders. The laptop features an NVIDIA Blackwell RTX GPU, up to 1…
An open-source developer released NBD-VRAM, a tool that creates swap space on consumer NVIDIA GeForce GPUs under Linux. The software targets laptop users with soldered memory who need additional syste…
Researchers have developed DiffusionBlocks, a framework that partitions transformer neural networks into independently trainable blocks to reduce memory requirements proportionally while maintaining c…
A developer has released tiny-vllm, a high-performance LLM inference engine written in C++ and CUDA that serves as a smaller sibling to the vLLM project. The open-source repository includes both the f…
A developer benchmarked the Qwen3.6 27B model on Modal using llama.cpp, deploying a serverless pipeline that downloads GGUF shards from Hugging Face and runs perplexity evaluation on an A100-80GB GPU.…
An eBPF agent that attaches to the CUDA runtime, CUDA driver, and Linux kernel scheduler simultaneously can trace a GPU stall back to the exact Python source line that triggered it. The tool correlate…