Skip to content

Commit 4d5aa35

Browse files
unamedkrclaude
andcommitted
README: lead with 7x context benefit, not implementation detail
Tagline changed from "Embeddable LLM inference in pure C" to "LLM inference with 7x longer context — pure C, zero dependencies". Adds "Lossless KV cache compression" to subtitle. Both EN and KO. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1 parent dbabab0 commit 4d5aa35

2 files changed

Lines changed: 6 additions & 6 deletions

File tree

README.ko.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -2,11 +2,11 @@
22
<img src="docs/assets/hero.png" alt="quant.cpp" width="600">
33
</p>
44

5-
<h3 align="center">순수 C로 만든 임베더블 LLM 추론 엔진</h3>
5+
<h3 align="center">7배 긴 컨텍스트를 만드는 LLM 추론 엔진 — 순수 C, 의존성 제로</h3>
66

77
<p align="center">
8-
<a href="#-단일-헤더-모드"><b>quant.h</b></a> 단일 헤더 라이브러리로도 제공됩니다.<br>
9-
67K LOC. 외부 라이브러리 없음. 오후 한나절이면 전체 코드를 읽을 수 있습니다.
8+
무손실 KV 캐시 압축. <a href="#-단일-헤더-모드"><b>quant.h</b></a> 단일 헤더 라이브러리로도 제공됩니다.<br>
9+
67K LOC. 임베딩 가능. 오후 한나절이면 전체 코드를 읽을 수 있습니다.
1010
</p>
1111

1212
<p align="center">

README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -2,11 +2,11 @@
22
<img src="docs/assets/hero.png" alt="quant.cpp" width="600">
33
</p>
44

5-
<h3 align="center">Embeddable LLM inference in pure C</h3>
5+
<h3 align="center">LLM inference with 7x longer context — pure C, zero dependencies</h3>
66

77
<p align="center">
8-
Also ships as <a href="#-single-header-mode"><b>quant.h</b></a> — a single-header library.<br>
9-
67K LOC. No external libraries. Read it in an afternoon.
8+
Lossless KV cache compression. Also ships as <a href="#-single-header-mode"><b>quant.h</b></a> — a single-header library.<br>
9+
67K LOC. Embeddable. Read it in an afternoon.
1010
</p>
1111

1212
<p align="center">

0 commit comments

Comments
 (0)