Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
language: en
|
| 4 |
+
tags:
|
| 5 |
+
- efficient-inference
|
| 6 |
+
- quantization
|
| 7 |
+
- speculative-decoding
|
| 8 |
+
- kv-cache
|
| 9 |
+
- llm-optimization
|
| 10 |
+
- tiny-models
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
# Tiny-Inference-Optimizer-Suite
|
| 14 |
+
|
| 15 |
+
> Cost-aware inference optimizer that auto-selects best quantization + speculative decoding + KV-cache compression strategy.
|
| 16 |
+
|
| 17 |
+
**Author:** Samudhan (@samudhan2003) | Built from Mobile + Colab, Harur, India
|
| 18 |
+
**Goal:** Research Scientist Internship - Stanford HAI / Baseten
|
| 19 |
+
|
| 20 |
+
This is my flagship artifact combining 3 research threads into
|