# Amp — Amp Tab 30% Faster

- Company: Amp (ampcode.com)
- Announced: 2025-07-30
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://ampcode.com/news/amp-tab-30-percent-faster
- Record: https://forck.live/items/7824-amp-tab-30-faster
- Subject: Amp
- Models affected: Amp Tab

Amp announced that response times of Amp Tab, its in-editor completion engine, are now 30% faster, with up to 50% improvements during peak usage. The improvement was achieved through infrastructure optimization with Baseten, switching to TensorRT-LLM as the inference engine, implementing KV caching with speculative decoding, and using a modified lookahead decoding algorithm with improved n-gram candidate selection and variable-length speculations.

## Evidence

Verbatim from https://ampcode.com/news/amp-tab-30-percent-faster:

> Response times of Amp Tab , our in-editor completion engine, are now 30% faster, with up to 50% improvements during peak usage.

---

Record: https://forck.live/items/7824-amp-tab-30-faster
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md