91
Inside vLLM: Anatomy of a High-Throughput LLM Inference System (2025)
From paged attention, continuous batching, prefix caching, specdec, etc. to multi-GPU, multi-node dynamic serving at scale.
New
The latest blog posts to take off on Hacker News. 4,387 posts.
92
Faster floating point math with Rust's new API
Compilers have a hard time optimizing floating point math. Rust has a new API to fix this.
93
Pi's Minimalism Is Its Advantage
How Pi's minimal harness improves coding-agent cost and performance, with examples from Databricks and Shopify's pi-autoresearch extension.
94
Windows XP 2002 for the Itanium: Unbridled rage
This is exciting news, there is a fork of Qemu that has workable Itanium Merced emulation, and it’s good enough to run Windows XP/2003! Enter Malte Kuhlmann ‘s Qemu fork of syunnPC ‘s AI Itanium infused Qemu fork .
95
Branchless Rust: Making a Filter 4x Faster by Removing an If
Why a filter is slowest when it keeps half of random input, and what a branchless rewrite gains there and loses at 1%.
96
MkLinux and the pimped-out Apple Workgroup Server 9150
As is typical here in the Floodgap lab, it all started so innocently: rebuilding a flaky Apple Workgroup Server 9150, the odd duck of the Wo...
97
But can your calculator run Linux?
Published: 01-08-2026 20:08 | Author: Remy van Elst | Text only version of this article
98
Algorithms on billion-scale graph using 10GB RAM: I love DataFusion
In a previous post, I was sceptical about using Apache DataFusion for graph analytics. However, after some thought and experimentation, I changed my mind. I have reconsidered my approach and now have a working implementation of basic graph algorithms, such as WCC, PageRank and MSSP. For example, I can identify weakly…
99
The session you cannot take with you
Inference APIs are filling sessions with encrypted reasoning, hidden search results, opaque compaction, and encrypted subagent messages. A growing form of lock-in.
100
State of multi-player Wayland
I've been fascinated by the idea of attaching multiple mice to one computer, and then having multiple mouse cursors inside of one desktop environment!
101
How Do I Profile eBPF Code?
If we are running any eBPF workload or writing eBPF code, we want to measure its performance impact, and in this post we will demonstrate an example of how to do it. In this example, our goal is to measure the performance of file open operations, one of the most critical functions in the OS. Our code used file open…
102
PGSimCity - How PostgreSQL Works
An independent, non-commercial educational visualization of PostgreSQL internals. Not affiliated with Electronic Arts.
103
Watching Go's new garbage collector move through the heap
Go 1.26 made Green Tea the default GC. We observe its cache-friendliness with perf, visualize the heap to see how Go allocates, and poke at a sparse-page problem a non-moving collector like Go's struggles with.
104
Everyone should know SIMD
SIMD has a reputation for being complex. I've met many very good software engineers who dismiss it as something too complex to learn or a niche optimization meant for only the highest-performance software, not useful in everyday programming.
105
Running Doom on Our Custom CPU and Going Viral
I get kidnapped by the MIG while adding DDR3 to our CPU
106
Designing an Ethernet Switch ASIC
Designing the world's first open source Ethernet switch ASIC. An unmanaged cut-through 3-port 100Mbps switch fabbed on Global Foundries 180 nm.
107
ECC and DDR5
Hamming Codes ECC RAM corrects errors that occur in memory before it gets to the CPU. The most common form of ECC is the Hamming Code [1] which when it has R redundant bits can correct single bit e…
108
Frame – Linux X server in Assembly
Philosophy - Sciences - Geekery - Art - Life - Coaching - Fun < Simplify Everything
109
Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK
I built a device to measure end-to-end input latency, then used it to find out what actually moves the needle.
110
The Zen of Parallel Programming
As I continue reading An Introduction to Parallel Programming, I cannot help but notice a connection between communication among processors, communication among human beings, and communication within the individual self....
111
Reviving a 15-year-old netbook with Arch Linux
KO | EN | Discussions on HN I still have a netbook I bought back in 2009. The ASUS Eee PC 1000HE has an Intel Atom N280 and 1GB of DDR2 RAM. The Atom N series was Intel’s line of cheap, low-performance CPUs for netbooks. The chip has 56KB of L1 cache and 512KB of L2 cache, and its clock speed is 1.6...
112
Job queues are deceptively tricky
A worked out example of different job queueing semantics and how they affect workloads.
113
Linux on the Sega 32X. Who needs hardware synchronization primitives anyway?
How wanting more is not always better
114
Benchmarking 15 “E-Waste” GPUs with Modern Workloads
Decommissioned enterprise tesla GPUs are widely available and extremely cheap. In this post, I benchmark tesla GPUs to see if they are useful
115
Quadrupling code performance with a "useless" if
So I was optimizing a domain-specific compressor the other day, as one does. One important problem was chunking the input string and optimally choosing the most compact encoding for each chunk (different encodings compress different characters better, so where to split is not immediately obvious). The previous post…
116
Your code is fast if you're lucky
Recently, while working on an optimized Quicksort implementation, I came across a rather interesting quirk. Modern compilers (especially Clang) optimize loops using fast, branch-free instructions - provided you use the right programming style.
117
Remote Attestation
If it quacks like a duck...
118
How to Build a Minimal ZFS NAS Without Synology, QNAP, TrueNAS (2024)
If you need a basic NAS and don't care about GUI features, it is suprisingly simple to set up a ZFS dataset and share it over the network using Samba.
119
Girls just wanna have fast MPMC queues with bounded waiting
Disclaimer: An earlier version of this post claimed the structure is wait-free, this is incorrect. Being wait-free requires that failure or suspension of any thread can’t cause failure or suspension of another thread. This queue in fact does not fulfill that requirement. The main section which discusses the wait…
120
Linux on the Atari Jaguar
The challenges around porting Linux to an old videogame console by Atari