871
FreeNAS and TrueNAS Are Unifying
FreeNAS and TrueNAS have been separate-but-related members of the #1 Open Source storage software family since 2012.
Topics /
Systems & Performance
The most popular blog posts about systems & performance on Hacker News. 2,560 posts.
872
File System Improvements to the Windows Subsystem for Linux
Access to this page requires authorization. You can try signing in or changing directories .
873
How Precision Time Protocol is being deployed at Meta
Implementing Precision Time Protocol (PTP) at Meta allows us to synchronize the systems that drive our products and services down to nanosecond precision. PTP’s predecessor, Network Time Protocol (…
874
Paving the way to efficient architectures: StripedHyena-7B
StripedHyena-7B is an open-source model built beyond the Transformer architecture, matching Llama-2 and Mistral 7B while running faster on long sequences.
875
A Brief History of High Availability
The perennial question of homo sapiens is, 'How did we get here?' Today we're going to take a crack at answering that: where 'here' is defined as 'high availability for web services'.
876
My Fear of Commitment to the First CPU Core
On this Valentine's Day Weekend I share the heartbreak that caused my fear of commitment to the 1st CPU Core of any socket (not just core 0).
877
Fast and flexible observability with canonical log lines
Canonical log lines are a lightweight, flexible, and technology-agnostic technique for observability that are powerful and easy to implement.
878
June 30th, 2024, will bring the End of Life (EOL) of CentOS Linux (2023)
Upgrade CentOS and Red Hat Enterprise Linux 7 to supported systems with Red Hat's in-place solutions
879
880
881
Running the Steam Deck’s OS in a virtual machine using QEMU
The Steam Deck is a handheld gaming computer that runs a Linux-based operating system called SteamOS. The machine comes with SteamOS 3 (code name “holo” ), which is in turn based on Arch Linux.
882
883
884
EC2 I/O
SentinelOne unifies AI-powered endpoint, cloud, identity, and data protection—enhanced by our Security Data Lake for seamless and efficient cybersecurity.
885
Yes, the 8086 wanted to be mechanically translatable from the 8080, but
So many addressing modes, so little space.
886
Real-time LLM Inference on Standard GPUs: 3k tokens/s per request
Today, Kog AI launches a tech preview of the Kog Inference Engine (KIE): 3,000 output tokens/s per request on 8× AMD MI300X GPUs and 2,100 on 8× NVIDIA H200 (FP16, no speculative decoding). This preview runs a 2B model, with support for large third-party MoE models coming next at similar speeds.
887
Consistency diffusion language models: Up to 14x faster, no quality loss
Standard diffusion language models can't use KV caching and need too many refinement steps to be practical. CDLM fixes both with a post-training recipe that enables exact block-wise KV caching and trajectory-consistent step reduction — delivering up to 14.5x latency improvements
888
OpenBSD: How it all started
OpenBSD remains a crucial yet largely unacknowledged player in the open-source field.
889
Jepsen: Etcd 3.4.3
The etcd key-value store is a distributed system intended for use as a coordination primitive. Like Zookeeper and Consul , etcd stores a small volume of infrequently-updated state ( by default, up to 8 GB ) in a key-value map, and offers strict-serializable reads, writes and micro-transactions across the entire…
890
891
ClickHouse Keeper: A ZooKeeper alternative written in C++
Read about why we built a resource-efficient alternative for Zookeeper from scratch in C++, what our next big step with it is, and how you can join the Keeper community.
892
New Ghostscript PDF interpreter
Details for Ghostscript's new PDF interpreter
893
Analysis and Exploitation of a Linux Kernel Vulnerability
FortiMail Workspace Security secures user-facing apps from advanced threats that target Email, Browsers, Collaboration Tools and Cloud Storage Apps.
894
Introducing Docker for Windows Server 2016
Docker is a founding member of the Blueprint Alliance, a 12-company reference architecture for securing AI agents, built around four governance questions.
895
896
897
898
899
Microsoft Zero and DeepSpeed: Memory Efficient Large Neural Network Training
The latest trend in AI is that larger natural language models provide better accuracy; however, larger models are difficult to train because of cost, time, and ease of code integration. Microsoft is releasing an open-source library called DeepSpeed, which vastly advances large model training by improving scale, speed…
900
LXC vs. Docker
Are you confused about whether to use LXC or Docker for your containerization needs? This article compares the two container platforms in terms of ...