GPU Forecasters: Language Models as Selective Surrogates for Kernel Optimization
The paper discusses the use of language models (LLMs) as surrogates for optimizing GPU kernel performance. It highlights the challenges of evaluating kernel performance on GPUs due to high costs and proposes a method for LLMs to forecast kernel performance. The findings suggest that LLMs can enhance kernel search efficiency and lead to the discovery of faster kernels.
- ▪GPU kernels are essential for deep learning but require costly evaluations on hardware for optimization.
- ▪The study explores how LLMs can act as selective surrogates to forecast kernel performance, reducing the need for extensive GPU evaluations.
- ▪Experiments show that LLMs can accurately predict kernel performance and improve search efficiency through reinforcement learning.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 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 | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2605.31464 |
| Publication time | Wed, 03 Jun 2026 04:51:02 +0000 |
| Retrieval time | 2026-06-03T05:11:55.598Z |
| Last seen | 2026-06-03T05:11:55.598Z |
| 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 | 0HS-kujUgqpe |
| 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
Computer Science > Machine Learning arXiv:2605.31464 (cs) [Submitted on 29 May 2026] Title:GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization Authors:Zaid Khan, Justin Chih-Yao Chen, Jaemin Cho, Elias Stengel-Eskin, Mohit Bansal View a PDF of the paper titled GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization, by Zaid Khan and Justin Chih-Yao Chen and Jaemin Cho and Elias Stengel-Eskin and Mohit Bansal View PDF Abstract:GPU kernels are the workhorse of modern deep learning, and optimizing them (via evolutionary search or coding agents) usually requires repeated measurement on target hardware.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
