Qualcomm-owned Modular released Mojo 1.0 on August 11 with its first stability guarantees and open-sourced the compiler, toolchain, and standard library under Apache 2.0 with LLVM exceptions on August…
A developer published a tutorial on building a vision-language robot pipeline that combines camera perception with natural-language instructions on NVIDIA Jetson hardware running ROS 2. The guide walk…
Inferact, founded by the creators and core maintainers of vLLM, is hiring University of Waterloo co-op students for an on-site Inference Engineering co-op in San Francisco, with pay not published. The…
JulianFlux has open-sourced a research repository, julianflux-research, containing a Python prototype and adversarial benchmark that the project claims achieves a 0.0% hallucination rate where standar…
Crusoe, a vertically integrated AI infrastructure company, is hiring a Staff Applied AI Inference Engineer in San Francisco with a salary range of $215,000–260,000 per year, which sits 8% above the $2…
NVIDIA's CUDA Multi-Process Service (MPS) enables concurrent kernel execution across multiple processes, improving GPU utilization compared to default time-slicing, according to a technical blog post …
A developer's source-code walkthrough of vLLM 0.22's V1 execution path traces a single offline inference request from the LLM.generate() API through inter-process communication, scheduling, GPU execut…
A user named Stormpie reported on a forum that their pottery dating machine 'terraID' fails with 'RuntimeError: No CUDA GPUs are available' when clicking the 'Analyze' button, despite the app running …
Wafer, an AI company, published a curated reading list for learning GPU performance engineering and production inference, ordered from a single inference request to distributed systems and featuring p…
A user reports that Qwen-Image-Edit-2511 struggles with one-to-one replacement of multiple identical objects in a scene, often removing all but one instance or misaligning viewpoints despite reference…
Optimizing CUDA kernels manually is becoming a specialized art, with developers moving beyond basic implementations to structured workflows that prioritize profiling-first approaches using NVIDIA Nsig…
NanoLM Studio V4, a local desktop workbench for building small decoder-only language models, has been publicly released by its developer. The Tk-based application integrates document ingestion, ByteLe…
Nvidia may acquire Hugging Face to create a unified AI stack from silicon to deployed models, according to an analysis. The potential merger would streamline model optimization, compute integration, a…
NVIDIA Dynamo, an open-source inference framework, has been deployed with the vLLM backend to serve chat completion requests in both aggregated and disaggregated configurations. The deployment involve…
PicoLM v1.0-rc1, an LLM inference engine written in C99, has been released, supporting llama-2, GPT-2, Qwen 3.6/3.8(+MoE), and Gemma-3n models. The engine features CPU SIMD acceleration, CUDA/HIP supp…
NVIDIA published a step-by-step tutorial demonstrating how to debug, benchmark, and optimize CUDA code using modern tools such as Compute Sanitizer, Nsight Systems, NVTX, CUB, and CCCL, applied to an …
A new technical blog post by Iaroslav Elistratov presents a visual guide to building a B200 attention kernel from scratch in CUDA and PTX, achieving 94.4% of FlashAttention-4 performance on 4K, 8K, an…
Salvatore Sanfilippo, the creator of Redis known as antirez, demonstrated DeepSeek V4 Flash with vision running locally on a Mac M5 Max on September 1, 2026, and announced that Metal, CUDA, and ROCm b…
At Hot Chips 2026, NVIDIA detailed its plans to bring RISC-V CPUs into its GPU platforms, outlining requirements for CUDA and NVLink Fusion integration. The company highlighted RVA23 profiles and the …
Patent filings at the intersection of AI and semiconductors increased 114% over the past five years, outpacing the broader sector's 78% growth, according to a report by IP management provider Anaqua. …