AI Engineering Lab commited on
Commit ·
22804ce
1
Parent(s): 571e9fb
Add HuggingFace Space frontmatter
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# llama-cpp-turboquant-guide
|
| 2 |
|
| 3 |
<div align="center">
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: TurboQuant on RTX 3090 — 100K Context, 4.3x KV-Cache Compression
|
| 3 |
+
emoji: 🚀
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: purple
|
| 6 |
+
sdk: static
|
| 7 |
+
pinned: true
|
| 8 |
+
license: cc-by-4.0
|
| 9 |
+
tags:
|
| 10 |
+
- llm
|
| 11 |
+
- quantization
|
| 12 |
+
- kv-cache
|
| 13 |
+
- turboquant
|
| 14 |
+
- benchmark
|
| 15 |
+
- rtx3090
|
| 16 |
+
- consumer-hardware
|
| 17 |
+
- mistral
|
| 18 |
+
- llama-cpp
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
# llama-cpp-turboquant-guide
|
| 22 |
|
| 23 |
<div align="center">
|