# kernels Published articles for kernels. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## OpenVDB Introduces SIMD Framework With Some 2~4x Performance Improvements DevFeed: [OpenVDB Introduces SIMD Framework With Some 2~4x Performance Improvements]() Original publisher: [Read original article]() Author: Michael Larabel Published: 2026-09-16T10:05:23Z Content type: news Language: en Sources: [Phoronix]() Topics: [Data structures](), [Tooling](), [x86](), [releases](), [cudnn](), [Open Source]() Tags: [avx](), [command-line](), [cuda](), [data](), [data-structure](), [desktop-linux](), [github](), [kernels](), [linux-benchmarking](), [linux-hardware-benchmarks](), [linux-hardware-reviews](), [linux-how-to](), [linux-performance](), [linux-server-benchmarks](), [open-source-graphics](), [performance](), [phoronix](), [phoronix-test-suite](), [release](), [ubuntu-benchmarks](), [ubuntu-hardware](), [x86]() ### AI overview OpenVDB 13.1 introduces a SIMD framework using Agner Fog's VectorClass Library for explicit x86 vectorization up to AVX-512. Adapted point transfer algorithms reportedly achieve 2x to 4x performance improvements on modern AVX-512 x86_64 CPUs. The release also includes NanoVDB CUDA resource-management and kernel improvements, plus updates to vdb_tool. ### Source excerpt OpenVDB is the sparse volume data structure and tooling library maintained by the Academy Software Foundation. OpenVDB in turn is used by various CGI software for dealing with sparse volumetric data such as Houdini, RenderMan, and Cinema 4D to the open-source Blender. It's even won an Academy Award for technical achievement while now in 2026 it's finally establishing a SIMD framework for better leveraging modern x86 ISA capabilities... ## \[$\] Adding BPF to blk-iocost DevFeed: [\[$\] Adding BPF to blk-iocost]() Original publisher: [Read original article]() Author: corbet Published: 2026-09-15T14:37:30Z Content type: article Language: en Sources: [LWN.net]() Topics: [Kernel](), [IO](), [ordering](), [Operating system]() Tags: [kernels](), [loading](), [ordering](), [performance]() ### AI overview This article discusses a patch series that would make the Linux blk-iocost I/O controller more flexible by allowing a BPF program to make cost decisions. It places the change in the context of block I/O scheduling for modern solid-state drives, where fairness and high throughput are important. ### Source excerpt The scheduling of block I/O requests has long been a challenge for operating-system kernels. For many years, the performance characteristics of rotating drives meant that putting considerable resources into request ordering was worthwhile. In a world with fast, solid-state drives, scheduling is more concerned with enforcing fairness between competing users while being fast enough to keep up with drives that can perform millions of I/O operations per second. The blk-iocost I/O controller was designed for the solid-state world and generally performs well, but there is always a desire to do better. This patch series from Tao Cui aims to make blk-iocost more flexible by enabling the loading of a BPF program to make cost decisions. ## More than 9,000 patches total in the seven stable kernels for Monday DevFeed: [More than 9,000 patches total in the seven stable kernels for Monday]() Original publisher: [Read original article]() Author: jzb Published: 2026-09-14T13:00:07Z Content type: news Language: en Sources: [LWN.net]() Topics: [kernels]() Tags: [kernels](), [upgrade]() ### AI overview Seven stable Linux kernels have received updates totaling more than 9,000 patches, including over 1,800 patches in version 7.2.6. Users are advised to upgrade. ### Source excerpt Greg Kroah-Hartman has announced the 7.2.6, 6.18.52, 6.12.110, 6.6.157, 6.1.188, 5.15.221, 5.10.270 stable kernels. According to Kroah-Hartman, this batch may set a record for the number of patches with more than 9,000 in total between them. There are more than 1,800 patches in 7.2.6 alone. Users of these kernels are, of course, advised to upgrade. ## BFS File-System Being Removed For Linux 7.4 DevFeed: [BFS File-System Being Removed For Linux 7.4]() Original publisher: [Read original article]() Author: Michael Larabel Published: 2026-09-13T11:03:26Z Content type: news Language: en Sources: [Phoronix]() Topics: [Filesystems](), [Linux](), [kernels](), [Unix](), [boot]() Tags: [boot](), [bootloader](), [desktop-linux](), [filesystem](), [filesystems](), [kernels](), [linux](), [linux-benchmarking](), [linux-hardware-benchmarks](), [linux-hardware-reviews](), [linux-how-to](), [linux-performance](), [linux-server-benchmarks](), [open-source-graphics](), [os](), [phoronix](), [phoronix-test-suite](), [systems](), [technical](), [ubuntu-benchmarks](), [ubuntu-hardware]() ### AI overview BFS, the obsolete UnixWare boot-partition filesystem, is slated for removal from the Linux kernel in version 7.4. The article cites its extremely limited functionality, lack of likely users, and broader efforts to reduce maintenance burdens from rarely used filesystems. ### Source excerpt The latest upstream file-system to be removed from the mainline Linux kernel is... BFS... ## Two stable kernel updates for Friday DevFeed: [Two stable kernel updates for Friday]() Original publisher: [Read original article]() Author: jzb Published: 2026-09-11T13:27:35Z Content type: news Language: en Sources: [LWN.net]() Topics: [kernels]() Tags: [kernel](), [kernels](), [release](), [updates]() ### AI overview Greg Kroah-Hartman announced stable kernel updates 7.2.5 and 6.18.51, each containing more than 550 patches with fixes throughout the tree. Users are advised to upgrade. ### Source excerpt Greg Kroah-Hartman has announced the release of the 7.2.5 and 6.18.51 stable kernels. There are more than 550 patches in each with fixes throughout the tree; users are advised to upgrade. ## Mold High Speed Linker Being Rewritten In Rust, Hopes To Be The Default Linker On Linux DevFeed: [Mold High Speed Linker Being Rewritten In Rust, Hopes To Be The Default Linker On Linux]() Original publisher: [Read original article]() Author: Michael Larabel Published: 2026-09-11T13:21:42Z Content type: news Language: en Sources: [Phoronix]() Topics: [Rust](), [Linux](), [Programming](), [toolchain]() Tags: [compatibility](), [desktop-linux](), [firmware](), [kernels](), [linux](), [linux-benchmarking](), [linux-hardware-benchmarks](), [linux-hardware-reviews](), [linux-how-to](), [linux-performance](), [linux-server-benchmarks](), [open-source](), [open-source-graphics](), [performance](), [phoronix](), [phoronix-test-suite](), [rust](), [speed](), [ubuntu-benchmarks](), [ubuntu-hardware]() ### AI overview The Mold high-speed linker is being rewritten from C++ in Rust for Mold 3.0. Its goals include preserving Mold 2.x performance, improving safety, supporting missing linker-script features, and potentially adding incremental linking. ### Source excerpt The Mold high performance linker that typically outperforms the likes of LLVM lld, GNU LD, Wild, and others is being rewritten in the Rust programming language and also has an ambitious goal of being adopted as the default linker on Linux systems... ## High-Throughput Structure Prediction with BioNeMo Inference Runtime DevFeed: [High-Throughput Structure Prediction with BioNeMo Inference Runtime]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-09-10T15:00:00Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [AI, ML & Data Engineering]() Tags: [bionemo](), [cuda](), [cuda-graphs](), [data-center-cloud](), [data-science](), [drug-discovery](), [gpu](), [healthcare-life-sciences](), [how-to](), [hpc-scientific-computing](), [inference](), [integration](), [kernels](), [model](), [models](), [node](), [nvidia](), [python](), [pytorch](), [resource](), [scale](), [simulation-modeling-design](), [tokenization](), [torch](), [tutorial](), [workflow]() ### AI overview A tutorial on using NVIDIA BioNeMo Inference Runtime to accelerate biomolecular structure-prediction models on GPUs. It covers the end-to-end Boltz2 workflow, PyTorch integration, input requirements, and Ray-based single-node throughput scaling. ### Source excerpt Biomolecular structure prediction is now often run at proteome scale, where the goal is to move an entire worklist through the pipeline efficiently. NVIDIA... ## Introducing CUDA Rust: Two Tracks for Writing GPU Kernels DevFeed: [Introducing CUDA Rust: Two Tracks for Writing GPU Kernels]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-09-08T12:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [GPU](), [Code generation](), [toolchain](), [C++]() Tags: [c-plus-plus](), [cuda](), [cuda-tile](), [data-science](), [developer-tools-techniques](), [dynamo](), [gpu](), [kernels](), [nemo-retriever](), [open-source](), [programming-languages-compilers](), [rust](), [toolchains]() ### AI overview NVIDIA introduces CUDA Rust for writing GPU kernels natively in Rust and compiling them to PTX. The article explains the SIMT and Tile programming tracks, recommends Tile as the default, and describes cuda-oxide's Rust-based code-generation path. ### Source excerpt In September 2026, NVIDIA announced it is leaning into native GPU programming in Rust. CUDA C++ and CUDA Python are mature, enterprise-grade toolchains, and... ## Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI DevFeed: [Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI]() Original publisher: [Read original article]() Author: Nico Martin; Joshua Published: 2026-09-01T00:00:00Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [webgpu](), [Local AI](), [Machine learning](), [Inference](), [benchmarking](), [GPU](), [Optimization]() Tags: [benchmark](), [gpu](), [hub](), [inference](), [javascript](), [kernels](), [local-ai](), [open-source](), [optimization](), [shaders](), [testing](), [webgpu]() ### AI overview Hugging Face releases @huggingface/kernels, a JavaScript library and collection of 207 versioned WebGPU kernel packages for browser-based local AI. It also introduces Fleet, a browser benchmarking and testing suite that gathers opted-in performance and correctness evidence across hardware. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## AWS Trainium Frontier competition: Co-design models and kernels on purpose-built AI chips DevFeed: [AWS Trainium Frontier competition: Co-design models and kernels on purpose-built AI chips]() Original publisher: [Read original article]() Author: Louise Ping; John Gray; Emily Webber; Josh Longenecker Published: 2026-08-10T20:23:04Z Content type: article Language: en Sources: [Amazon Science homepage]() Topics: [AI Chat]() Tags: [aws-trainium](), [chip-design](), [hardware](), [kernels](), [language-models](), [machine-learning](), [model-architecture](), [neurips](), [performance](), [training]() ### AI overview AWS Trainium Frontier is a competition for training language models from scratch on Trainium while co-designing architectures, optimizers, training loops, and optional custom kernels under fixed compute and time budgets. ### Source excerpt A competition with a finalist ceremony during NeurIPS 2026, challenging researchers to train language models from scratch on Trainium, exploring what optimal architectures look like when the hardware changes. ## GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model DevFeed: [GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model]() Original publisher: [Read original article]() Author: Darren Liu; Huayu Li; Raghav Boinepalli; Yuzhen Huang; Jackie (Jiaqi) Xu; Richard Qiu; Chunzhi Yang; Rich Zhu; Dev (Devashish) Shankar; Huaqing Xiong Published: 2026-08-03T18:00:17Z Content type: article Language: en Sources: [Engineering at Meta](), [Meta AI Research](), [Meta ML Applications]() Topics: [recommendation systems](), [networking]() Tags: [ads](), [ai-infrastructure](), [ai-research](), [data-infrastructure](), [gpu](), [hardware](), [kernels](), [llm](), [meta](), [ml-applications](), [networking](), [recommendation-systems](), [training]() ### AI overview Meta describes training its GEM ads recommendation foundation model at LLM scale. The article covers recommendation-specific kernels, ultra-low-precision training, and topology-aware parallelism that doubled end-to-end training efficiency to 20-25% MFU while increasing training FLOPs fourfold. ### Source excerpt Meta's Generative Ads Recommendation Model (GEM), the foundation model behind ads recommendations across Instagram and Facebook, now trains at LLM scale on several thousand of the latest-generation GPUs. This post goes into the details on how we achieved: doubling end-to-end (E2E) training efficiency to 20-25% Model FLOPs Utilization (MFU) while scaling training FLOPs 4x in [...] Read More... The post GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model appeared first on Engineering at Meta. ## Bringing Nunchaku 4-bit Diffusion Inference to Diffusers DevFeed: [Bringing Nunchaku 4-bit Diffusion Inference to Diffusers]() Original publisher: [Read original article]() Author: Pham Hong Vinh; Sayak Paul Published: 2026-07-23T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [diffusers](), [Inference](), [quantization](), [diffusion-transformers](), [NVFP4](), [GPU](), [NCCL]() Tags: [diffusers](), [diffusion](), [diffusion-transformers](), [gpu](), [guide](), [hardware](), [inference](), [kernels](), [memory](), [nvfp4](), [nvidia](), [quantization](), [speed]() ### AI overview This article explains how Nunchaku brings 4-bit diffusion inference to Hugging Face Diffusers. It describes SVDQuant's W4A4 approach, integration of pre-quantized checkpoints without local CUDA compilation, and hardware requirements for NVFP4 and INT4 variants. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## 🤗 Kernels: Major Updates DevFeed: [🤗 Kernels: Major Updates]() Original publisher: [Read original article]() Author: Sayak Paul; Daniël de Kok; David Holtz Published: 2026-07-06T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [kernels](), [Security](), [Open Source](), [Nix](), [Git](), [systems]() Tags: [git](), [hub](), [kernel-builder](), [kernels](), [open-source](), [optimization](), [sandbox](), [security](), [updates]() ### AI overview Hugging Face's Kernels project introduces a first-class "kernel" repository type on the Hub, allowing users to inspect supported accelerators, operating systems, and backend versions. The update also adds trusted publishers, code signing, reproducible Nix-based builds, and embedded Git source identifiers to improve security and provenance. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel DevFeed: [Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel]() Original publisher: [Read original article]() Author: Adil Asif; Alexandros Koumparoulis; Wenwen Gao; Sylendran Arunagiri; David Messina; Bernard Nguyen Published: 2026-06-24T16:00:13Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [NeMo](), [Fine-tuning](), [AI Models](), [Mixture of Experts (MoE)](), [distributed-training](), [Generative AI](), [Artificial Intelligence](), [GPU](), [PyTorch](), [vllm](), [sglang]() Tags: [ai](), [ai-models](), [building](), [compute](), [distributed-training](), [fine-tuning](), [framework](), [generative](), [generative-ai](), [gpu](), [infrastructure](), [kernels](), [memory](), [model](), [moe](), [nemo](), [nemotron](), [nvidia](), [open](), [transformers]() ### AI overview This article explains how NVIDIA NeMo AutoModel accelerates fine-tuning of mixture-of-experts models by extending Transformers v5 with Expert Parallelism, DeepEP fused all-to-all dispatch, and TransformerEngine kernels. It describes API compatibility, distributed execution, dynamic weight loading, and reported gains of 3.4-3.7x higher training throughput and 29-32% lower GPU memory use. ### Source excerpt NVIDIA NeMo AutoModel is an open library part of the NVIDIA NeMo framework for building custom generative AI models at scale. NeMo AutoModel builds cleanly on top of v5, adding Expert Parallelism, DeepEP fused all-to-all dispatch, and TransformerEngine kernels, and it leans on v5's dynamic weight loading to bring those optimizations to a broad and growing set of model families. ## Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP DevFeed: [Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP]() Original publisher: [Read original article]() Author: Aritra Roy Gosthipaty; Rémi Ouazan Reboul; Sergio Paniego; Pedro Cuenca; Sayak Paul Published: 2026-06-11T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [AI, ML & Data Engineering](), [cpu](), [jobs]() Tags: [cpu](), [cuda](), [deep-learning](), [gpu](), [jobs](), [kernels](), [liger](), [mlp](), [open-source](), [profile](), [pytorch](), [torch](), [traces]() ### AI overview A PyTorch profiling tutorial that moves from nn.Linear to a fused multilayer perceptron, explaining GPU kernels, CPU launch overhead, and tensor-transpose behavior in profiler traces. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler DevFeed: [Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler]() Original publisher: [Read original article]() Author: Aritra Roy Gosthipaty; Sayak Paul; Sergio Paniego; Rémi Ouazan Reboul; Pedro Cuenca Published: 2026-05-29T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [GPU](), [AI, ML & Data Engineering](), [cpu](), [jobs]() Tags: [cpu](), [cuda](), [gpu](), [guide](), [how-to](), [jobs](), [kernel](), [kernels](), [llm](), [open-source](), [profile](), [python](), [pytorch](), [torch](), [traces](), [training](), [tutorials]() ### AI overview A beginner-focused tutorial on using torch.profiler to inspect PyTorch execution, interpret CPU and GPU traces, and connect Python operations to CUDA kernels. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## From Exploit Code to Production Detection: Building a CVE-2026-31431 (Copy Fail) detection with Agents DevFeed: [From Exploit Code to Production Detection: Building a CVE-2026-31431 (Copy Fail) detection with Agents]() Original publisher: [Read original article]() Author: Ryan Simon Published: 2026-05-28T00:00:00Z Content type: article Language: en Sources: [Datadog Security Labs]() Topics: [Vulnerabilities](), [Linux](), [Detection engineering](), [kernels](), [Security](), [AI-assisted coding](), [Cryptography]() Tags: [agents](), [analysis](), [audit-trail](), [code](), [coding](), [engineering](), [kernel](), [kernels](), [linux](), [operations](), [security](), [vulnerabilities](), [vulnerability]() ### AI overview CVE-2026-31431, known as Copy Fail, allows an unprivileged local user to corrupt Linux page caches through AF_ALG sockets and escalate privileges to execute code as root. The article explains the exploit's kernel mechanisms and describes how Datadog Security Research used coding agents to develop and ship a detection in a single session. ### Source excerpt CVE-2026-31431 (Copy Fail) lets any unprivileged user corrupt the Linux page cache via AF_ALG sockets to escalate privileges. This post covers the exploit mechanics and how Datadog Security Research used coding agents to ship a detection content pack in a single session. ## Kubernetes v1.36: Tiered Memory Protection with Memory QoS DevFeed: [Kubernetes v1.36: Tiered Memory Protection with Memory QoS]() Original publisher: [Read original article]() Author: Qi Wang; Sohan Kunkerkar Published: 2026-04-29T18:35:00Z Content type: news Language: en Sources: [Kubernetes Blog]() Topics: [Kubernetes](), [configuration](), [observability](), [kernels]() Tags: [feature](), [kernels](), [kubernetes](), [memory](), [metrics](), [observability](), [v1]() ### AI overview Kubernetes v1.36 updates the alpha Memory QoS feature with opt-in memory reservation, tiered protection based on Pod QoS class, observability metrics, and a warning for kernels older than 5.9. Guaranteed Pods receive hard protection, Burstable Pods receive reclaimable soft protection, and BestEffort Pods remain fully reclaimable. ### Source excerpt On behalf of SIG Node, we are pleased to announce updates to the Memory QoS feature (alpha) in Kubernetes v1.36. Memory QoS uses the cgroup v2 memory controller to give the kernel better guidance on how to treat container memory. It was first introduced in v1.22 and updated in v1.27. In Kubernetes v1.36, we're introducing: opt-in memory reservation, tiered protection by QoS class, observability metrics, and kernel-version warning for memory.high. What's new in v1.36Opt-in memory reservation with memoryReservationPolicy v1.36 separates throttling from reservation. Enabling the feature gate turns on memory.high throttling (the kubelet sets memory.high based on memoryThrottlingFactor, default 0.9), but memory reservation is now controlled by a separate kubelet configuration field: None (default): no memory.min or memory.low is written. Throttling via memory.high still works. TieredReservation: the kubelet writes tiered memory protection based on the Pod's QoS class: Guaranteed Pods get hard protection via memory.min. For example, a Guaranteed Pod requesting 512 MiB of memory results in: $ cat /sys/fs/cgroup/kubepods.slice/kubepods-pod6a4f2e3b_1c9d_4a5e_8f7b_2d3e4f5a6b7c.slice/memory.min 536870912 The kernel will not reclaim this memory under any circumstances. If it cannot honor the guarantee, it invokes the OOM killer on other processes to free pages. Burstable Pods get soft protection via memory.low. For the same 512 MiB request on a Burstable Pod: $ cat /sys/fs/cgroup/kubepods.slice/kubepods-burstable.slice/kubepods-burstable-pod8b3c7d2e_4f5a_6b7c_9d1e_3f4a5b6c7d8e.slice/memory.low 536870912 The kernel avoids reclaiming this memory under normal pressure, but may reclaim it if the alternative is a system-wide OOM. BestEffort Pods get neither memory.min nor memory.low. Their memory remains fully reclaimable. Comparison with v1.27 behavior In earlier versions, enabling the MemoryQoS feature gate immediately set memory.min for every container with a memory request. memo ## Custom Kernels for All from Codex and Claude DevFeed: [Custom Kernels for All from Codex and Claude]() Original publisher: [Read original article]() Author: ben burtenshaw; Sayak Paul; Aritra Roy Gosthipaty; shaun smith Published: 2026-02-13T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [CUDA](), [Agent Skills](), [AI-assisted coding](), [PyTorch](), [diffusers](), [Large Language Model](), [GPU](), [kernel-builder]() Tags: [agent-skills](), [agents](), [benchmarks](), [claude-code](), [community](), [cuda](), [cursor](), [diffusers](), [gpu](), [kernels](), [memory](), [open-source](), [pytorch](), [transformers]() ### AI overview The article describes an agent skill that teaches coding agents to write production CUDA kernels. Claude and Codex were used to create working kernels for a diffusers pipeline and a transformers model, including PyTorch bindings and benchmarks. The skill packages GPU architecture, memory optimization, project structure, and integration expertise for on-demand use. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Redesigning my microkernel from the ground up DevFeed: [Redesigning my microkernel from the ground up]() Original publisher: [Read original article]() Author: January Published: 2026-01-12T00:00:00Z Content type: opinion Language: en Sources: [Drew DeVault]() Topics: [systems](), [Kernel](), [kernels](), [Development](), [Code](), [Unix]() Tags: [code](), [cpu](), [development](), [kernel](), [kernels](), [operating-systems](), [os](), [scheduler](), [systems](), [unix]() ### AI overview The author explains why the Helios microkernel project was abandoned after design and implementation problems, and describes starting Hermes from scratch while reusing selected code from Helios and Bunnix. Hermes is not yet feature-complete, but the author says it has a more robust design and supports symmetric multiprocessing. ### Source excerpt As you may recall, circa 2022-2023 I was working on a microkernel written in Hare named Helios. Helios was largely inspired by and modelled after the design of seL4 and was my first major foray into modern OS development that was serious enough to get to a somewhat useful state of functionality, with drives for some real hardware, filesystems, and an environment for running user programs of a reasonable level of sophistication. Helios development went strong for a while but eventually it slowed and eventually halted in a state of design hell. Since Helios was my first major OS project at this scale and with this much ambition, the design and implementation ended up with a lot of poor assumptions that made it a pretty weak foundation for building a complete OS upon. In late 2023 I more or less gave up on it and moved my OS development work out of the realm of writing code and back into the realm of thinking really hard about how to design operating systems. What followed was a couple of years of design thinking, developing small scale design experiments, and doing deeper research into prior art - reading papers and studying existing kernels. It was also during this period that I wrote Bunnix, a working Unix clone, motivated in part by a desire to gain some first-hand experience working in the design and implementation of Unix-style operating systems - a fertile environment for learning a lot of the nuts and bolts of OS implementations by working against a complete and proven design. In August I was finally prepared to have another go. I decided to start over from scratch, importing and adapting and rewriting code from Helios and Bunnix on an as-needed basis to speed things up, and writing from scratch anything where the lessons learned in hindsight outweighed the benefits of adapting existing code.1 The result is Hermes. Hermes has not yet reached feature parity with Helios, lacking some IPC features and an aarch64 port, but already it's significantly more robust and ## Easily Build and Share ROCm Kernels with Hugging Face DevFeed: [Easily Build and Share ROCm Kernels with Hugging Face]() Original publisher: [Read original article]() Author: Abdennacer Badaoui; Daniel Huang; colorswind; Zesen Liu Published: 2025-11-17T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [kernels](), [rocm](), [hugging face](), [PyTorch](), [Deep learning](), [Open Source](), [benchmarking](), [CUDA]() Tags: [amd](), [architectures](), [best-practices](), [build](), [building](), [compiler](), [compute](), [core](), [cuda](), [deep-learning](), [deployment](), [developer](), [gpu](), [hardware](), [hugging-face](), [innovation](), [kernels](), [open-source](), [pytorch](), [rocm]() ### AI overview This tutorial explains how to build, test, package, deploy, and share ROCm-compatible GPU kernels with Hugging Face's kernels library and kernel-builder. It focuses on integrating kernels with PyTorch and optimizing them for AMD GPUs, using a high-performance FP8 GEMM kernel for the AMD Instinct MI300X as an example. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## exploits.club Weekly Newsletter 86 - KSMBD 0Clicks, Apple Ends Memory Corruption, Mini-Kernels in Zig, And More DevFeed: [exploits.club Weekly Newsletter 86 - KSMBD 0Clicks, Apple Ends Memory Corruption, Mini-Kernels in Zig, And More]() Original publisher: [Read original article]() Author: exploits.club Published: 2025-09-18T15:00:23Z Content type: article Language: en Sources: [exploits.club]() Topics: [Hacking](), [Exploit](), [Linux Kernel](), [Security]() Tags: [apple](), [exploits](), [kernels](), [memory](), [newsletter](), [weekly]() ### AI overview A weekly newsletter covering OrangeCon videos, an open DistrictCon CFP, a Linux kernel ksmbd exploit write-up, DEF CON car-hacking challenges, and Apple's Memory Integrity Enforcement research. ### Source excerpt Write a weekly newsletter, they said. It will be fun, they said....Annnnnnyway 👇 In Case You Missed It... OrangeCon 2025 Videos Online - Hours of new content...go check it out! DistrictCon CFP Still Open - Get em in by the end of the month! Resources And Write-Ups From This ## From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels DevFeed: [From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels]() Original publisher: [Read original article]() Author: David Holtz; Daniël de Kok Published: 2025-08-18T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [CUDA](), [GPU](), [PyTorch](), [Deployment](), [build times](), [C++]() Tags: [c-plus-plus](), [cuda](), [deployment](), [ecosystem](), [gpu](), [guide](), [hub](), [kernels](), [kernels-community](), [optimization](), [pytorch]() ### AI overview A guide to building modern, production-ready CUDA kernels with Hugging Face Kernel Builder. It covers developing a custom RGB-to-grayscale kernel with PyTorch's C++ API, supporting multiple architectures, managing dependencies, and addressing production and deployment challenges. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Debian GNU/Hurd 2025 Released as an Official GNU/Hurd Port Snapshot DevFeed: [Debian GNU/Hurd 2025 Released as an Official GNU/Hurd Port Snapshot]() Original publisher: [Read original article]() Published: 2025-08-10T00:00:00Z Content type: release Language: en Sources: [GNU Hurd]() Topics: [Debian](), [systems]() Tags: [2025](), [debian](), [gnu-hurd](), [kernels](), [release](), [unix]() ### AI overview Debian GNU/Hurd 2025 is an official Debian GNU/Hurd port release based mostly on Debian sid sources from the stable Debian Trixie release in August 2025. It is not an official Debian release. GNU Hurd is described as a collection of servers running on the Mach microkernel to provide services traditionally implemented by a Unix kernel. ### Source excerpt Debian GNU/Hurd 2025 released! Details. It is with huge pleasure that the Debian GNU/Hurd team announces the release of Debian GNU/Hurd 2025. This is a snapshot of Debian "sid" at the time of the stable Debian "Trixie" release (Auguest 2025), so it is mostly based on the same sources. It is not an official Debian release, but it is an official Debian GNU/Hurd port release. Before posting questions on various webnews, please read [the FAQ][faq] which will answer most if not all of them. For release details, please read the announcement email. The GNU Hurd is the GNU project's replacement for the Unix kernel. It is a collection of servers that run on the Mach microkernel to implement file systems, network protocols, file access control, and other features that are implemented by the Unix kernel or similar kernels (such as Linux). More detailed. GNU Mach is the microkernel upon which a GNU Hurd system is based. It provides an Inter Process Communication (IPC) mechanism that the Hurd uses to define interfaces for implementing in a distributed multi-server fashion the services a traditional operating system kernel provides. More detailed. [Next page]()