speed

25 stories and discussions about speed, aggregated from every source we track.

1.

My last post on the Rust compiler’s performance was two months ago and a lot has happened since then.

67 points•patchunwrap•1 day ago•5 comments
2.

How a branch-free loop and byte-space arithmetic let GitHub case-fold every byte of code search at >45 GiB/s on a single core.

12 points•fanf•about 2 months ago•1 comment
3.

This week should have a little something for everyone. We’ve got bug squashing galore in preparation for Plasma 5.18, substantial speed improvements for wifi connection and Discover launch ti…

7 points•raymii•over 6 years ago•1 comment
4.

We see a lot of simple pen plotter projects around here, and while we appreciate them one and all, most of them are a little on the slow side. That’s OK — a glacial pace is sometimes al…

6 points•river•over 4 years ago•0 comments
6.

Maximizing perf on AI-SQL queries with the KV-optimal left-deep join

2 points•charles_irl•1 day ago•0 comments•
7.

Contribute to NycolazSec/tcpcat development by creating an account on GitHub.

2 points•tcpcat•4 days ago•0 comments•
8.
2 points•intrasight•5 days ago•1 comment•
9.
2 points•mooreds•7 days ago•0 comments•
10.
2 points•simonpure•10 days ago•0 comments•
11.

My last post on the Rust compiler’s performance was two months ago and a lot has happened since then.

1 points•ibobev•about 13 hours ago•0 comments•
12.

A shader editor for writing, debugging, and sharing.

1 points•ibobev•about 14 hours ago•0 comments•
13.

A speed-dating puzzle about moving sixteen people between four tables leads to finite fields, affine planes, and a surprisingly rich scheduling problem.

1 points•napping_penguin•1 day ago•1 comment•
14.

TensorFold's new inference engine delivers decode speeds over 62 tokens per second on a single stream and 119 across five, with prefill at 2,500 tokens per second and a 256k context window. It outperforms prior vLLM…

1 points•soltanov•1 day ago•0 comments•
15.
1 points•abhijithneil•2 days ago•0 comments•
16.

SWISS has launched high-speed in-flight internet services, with Starlink set to be installed across the airline's fleet by the end of 2029.

1 points•7777777phil•2 days ago•0 comments•
17.

Nearly SNFS-Speed Signature Forgery Sans Factoring N - ucsd-hacc/NSNFSSSFSFN

1 points•Garbage•4 days ago•0 comments•
18.

One of the most annoying myths in software development that just won’t die is the supposed tradeoff between speed and quality. The common thinking goes: quality, speed, cost - pick 2. And because time is money, this in…

1 points•mooreds•5 days ago•0 comments•
19.

Fork off LLama cpp that newly scales GPU 2x 4x etc also on big models not fully fitting in vram - neurall/llama.cpp

1 points•neuralll•6 days ago•1 comment•
20.

Starting with Feast v0.65, a new tighter integration between Feast and ScyllaDB brings vector search support and better performance to the online store. This post covers what changed, why teams outgrow their existing…

1 points•tzach•6 days ago•1 comment•
21.

Fixes WoW running at a third of its frame rate on Apple Silicon Macs: a tiny overlay that keeps macOS from parking the GPU at its minimum clock - chrisdecember/wow-mac-boost

1 points•nk_kolja•7 days ago•0 comments•
22.

The SQL parser powering pgdog.dev. Contribute to pgdogdev/pg_raw_parse development by creating an account on GitHub.

1 points•levkk•9 days ago•0 comments•
24.

This article discusses how the first move you make during an investigation can affect how quickly you come to a conclusion.

1 points•Sietsebb•over 2 years ago•0 comments
25.

ParparVM fixes pathological map misses and extends tagged boxed values. Probe counts, allocation coverage, and regressions show where ordinary Java collections became cheaper.

0 points•codenameone•10 days ago•0 comments

Related topics