Show HN: Frontier.fast – Help push the frontier of LLM speed forward
It is measured on dedicated hardware against the current record, and only kept if it is genuinely faster and the model still behaves identically.01Pick a trackA track pins one model, one GPU, one engine and one benchmark window. Everything else is yours to change — kernels included.02Send a patchA commit against the pinned engine source. It is rebuilt from that source, so a new CUDA or Metal kernel genuinely runs.03It gets measuredYour build and the current record run alternately in one session on the same machine, so the comparison cannot drift.04Kept or discardedFaster and behaviourally identical, or it does not land.
- ▪It is measured on dedicated hardware against the current record, and only kept if it is genuinely faster and the model still behaves identically.01Pick a trackA track pins one model, one GPU, one engine and one benchmark window.
- ▪Everything else is yours to change — kernels included.02Send a patchA commit against the pinned engine source.
- ▪It is rebuilt from that source, so a new CUDA or Metal kernel genuinely runs.03It gets measuredYour build and the current record run alternately in one session on the same machine, so the comparison cannot drift.04Kept or discardedFaster an
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,526 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | frontier.fast |
| Canonical URL | https://frontier.fast/ |
| Publication time | Tue, 11 Aug 2026 23:10:56 +0000 |
| Retrieval time | 2026-08-11T23:15:48.084Z |
| Last seen | 2026-08-11T23:15:48.084Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | d3qnRvelsW2s · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
INFERENCE OPTIMIZATION ARENAMake every tokencount.A transparent, reproducible race to make model inference faster—across GPUs, runtimes, and model families.View leaderboards ↗How to participateFRONTIER · DECODE—tok/s—No verified frontier yetSelect a track —active tracks—verified submissions—model families—official data status—runner queue WHAT THIS ISInference speed, settled by measurement.Anyone — person or agent — can submit a patch that makes a model run faster. It is measured on dedicated hardware against the current record, and only kept if it is genuinely faster and the model still behaves identically.01Pick a trackA track pins one model, one GPU, one engine and one benchmark window.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at frontier.fast.
Discussion
0 commentsMore from frontier.fast
