adaptq

High-performance C++17 KV cache compression engine for LLM inference with Python bindings, SIMD acceleration, and multi-backend support

A new way for AI to search for data
View on GitHub
8GitHub stars
341commits on v2
44forks
v0.2.3latest release, 2026-10-04

C++ 59.5%, Python 37.5%, CMake 1.4%, C 1.3% · created 2026-04-25 · last push 2026-10-06

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit fd9e7555cd. It is the newest commit on v2.

Selected work

Licence

The repository

NONE

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

NONE, with credit

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-10-28. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

attentionavx2cpu-optimizationinferencekv-cachellmpythonpytorch

Example questions

Inside the indexed corpus

Licence on GitHub and in the corpus

GitHub reported no licence for l3tchupkt/adaptq on 2026-10-29. At commit fd9e7555cd the LICENSE file was reviewed as NONE.

Contributors

LAKSHMIKANTHAN K (@l3tchupkt) has 13 selected repositories on the hub.

Their other repository pages: l3tchupkt/Claudex, l3tchupkt/claude-code, l3tchupkt/esp32-deauth-bypass, l3tchupkt/JSEye, l3tchupkt/PluginHunter, l3tchupkt/Bug-Bounty-Roadmap-2025.

Using XERJ with adaptq

The prompt

Paste it into your AI agent. It clones l3tchupkt/adaptq at the pinned commit and indexes it on your machine.

Search the GitHub repository l3tchupkt/adaptq with XERJ (https://hub.xerj.org/corpus/l3tchupkt--adaptq).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/l3tchupkt/adaptq adaptq && git -C adaptq checkout fd9e7555cd94661d37b2168e4d09a05fb4e20c4c
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./adaptq --url http://127.0.0.1:9200 --prefix adaptq --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: check the LICENSE file. Keep the copyright notice and credit the authors.

Related

Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.