HNHacker News
TopNewBestAskShowJobs

ashvardanian

4,506 karma · joined November 26, 2021

Bootstrapping <Unum.cloud> since 2015. Investing at <AAL.vc>. Hosting ML/Systems hackathons around the globe. Living between London, San Francisco, and Yerevan. Converting outrageous amounts of coffee into modest amounts of Assembly for Intel, Arm, and Nvidia chips. Maintaining FOSS libs deployed on ≫ 100M devices.

<ashvardanian.com>

<github.com/ashvardanian>

submissionscomments

Simdjson 5.0 Is Out

lemire.me·4 pts·ashvardanian·
0

Bridging Models' Internal States

mostik.ai·3 pts·ashvardanian·
0

Using AI to build your own software

lemire.me·6 pts·ashvardanian·
0

Show HN: ForkUnion v3 – Faster OpenMP-style thread-pool for C, C++, Rust, & Zig

github.com·3 pts·ashvardanian·
0

AI Model Co-Design: Hardware-Friendly LLM Design

developer.nvidia.com·2 pts·ashvardanian·
0

KinetIQ Ascend: Toward 100% Reliable Manipulation and Superhuman Speed

thehumanoid.ai·5 pts·ashvardanian·
2

Nvidia CUDA Python 1.0 and CUDA 13.3 Release

developer.nvidia.com·2 pts·ashvardanian·
0

Laguna XS.2 and Laguna M.1 by Poolside

poolside.ai·5 pts·ashvardanian·
0

FP8 Search and KV-Caching in USearch

unum.cloud·1 pts·ashvardanian·
0

Escaping the Fork: How Meta Modernized WebRTC Across 50 Use Cases

engineering.fb.com·3 pts·ashvardanian·
0

Porting Go's io package to C

antonz.org·6 pts·ashvardanian·
0

Schema as the Core of Reliability in AI Memory

xmemory.ai·6 pts·ashvardanian·
0

NumKong: 2'000 Mixed Precision Kernels for All

ashvardanian.com·47 pts·ashvardanian·
6

The State of Allocators in 2026

cetra3.github.io·2 pts·ashvardanian·
0

Recraft V4

recraft.ai·2 pts·ashvardanian·
0

Nebius to buy AI agent search company Tavily for 275M

nebius.com·2 pts·ashvardanian·
1

Running Async WebAssembly on Seastar's Reactor

rockwotj.com·3 pts·ashvardanian·
0

Open source USearch library jumpstarts ScyllaDB vector search

thenewstack.io·2 pts·ashvardanian·
0

Mixedbread: How We Built Multimodal Late-Interaction at Billion Scale

mixedbread.com·3 pts·ashvardanian·
0

Nvidia: Using Context as Training Data Unlocks Models That Learn at Test-Time

developer.nvidia.com·6 pts·ashvardanian·
0

Nvidia Kicks Off the Next Generation of AI with Rubin – Six New Chips

nvidianews.nvidia.com·15 pts·ashvardanian·
4

Building Code-Chunk: AST Aware Code Chunking

supermemory.ai·2 pts·ashvardanian·
0

Rust: Using String and andstr in your APIs

dx13.co.uk·3 pts·ashvardanian·
1

From Ts_rank to BM25. Introducing Pg_textsearch: True BM25 Ranking and Retrieval

tigerdata.com·2 pts·ashvardanian·
0

Full Unicode Search at 50× ICU Speed with AVX‑512

ashvardanian.com·217 pts·ashvardanian·
77

Emulating AVX-512 intrinsics in Miri

trifectatech.org·14 pts·ashvardanian·
0

Why we built Lightpanda in Zig

lightpanda.io·212 pts·ashvardanian·
187

Nvidia cuTile: Python DSL and a new IR for tile-based CUDA kernels

github.com·5 pts·ashvardanian·
0

SereneDB Secures $2.1M to Challenge the Status Quo of Search and Analytics

serenedb.com·13 pts·ashvardanian·
9

Evidently 0.7.17: open-source LLM tracing and dataset management

evidentlyai.com·1 pts·ashvardanian·
0
Page 1 of 13Next →