Show HN: Automatic deduction of FlashAttention kernel from ~25 lines of SQL
Sentiment Mix
Geography
Expert Signals
alxmrs
author • 1 mention
Hacker News
source • 1 mention
AI-Generated Claims
Generated from linked receipts; click sources for full context.
Show HN: Automatic deduction of FlashAttention kernel from ~25 lines of SQL.
Supported by 1 story
In this demo, we automatically deduce a FlashAttention kernel with ~25 lines of SQL, which just expresses vanilla attention.
Supported by 1 story
This is possible due to three portable SQL extensions that we're building: - xarray-sql: a library that efficiently represents petabyte scale array datasets in the cloud as tables (relations).
Supported by 1 story
- einfold: a modular query planner for fast tensor contractions in vanilla SQL, again, assuming the above array data model.My hope is that the relational model and algebra provide fresh perspectives on how we might do accelerator programming.
Supported by 1 story
Here, our thesis is that separating the logical layers in a tensor program from the physical layers is both more correct and more scalable.If the Bitter Lesson is a central dogma of machine learning, then why not formalize it with relational algebra?If this interests you and you'd like to tinker...
Supported by 1 story
Related Events
Hackers hijacked a Claude Code extension, exposing yet another new AI security risk - Fast Company
LLMs • 10/30/2026
Show HN: Spinf-serve – inference server for bulk scoring and decisions
Uncategorized • 10/31/2026
Anthropic: That Claude Code extension compromise… couldn't be us - The Register
LLMs • 10/31/2026
Cisco gives engineer unlimited AI tokens to rewrite legacy code
LLMs • 10/30/2026
In Other News: Anthropic Breach Dispute, UEFI Flaw Hits Most Servers, Cloudflare AI Data Leak - SecurityWeek
LLMs • 10/30/2026