docs: remove AWQ variants (AWQ lane paused; MLX focus)
Browse files
README.md
CHANGED
|
@@ -38,7 +38,6 @@ KV cache compression reduces the memory used by the attention cache during infer
|
|
| 38 |
|
| 39 |
| Technique | Where it's applied | Savings |
|
| 40 |
|-----------|-------------------|---------|
|
| 41 |
-
| Weight quantization (GGUF/MLX/AWQ) | Baked into model file | Reduces disk + weight memory |
|
| 42 |
| **RotorQuant KV cache** | At inference time | Reduces attention memory (critical for long context) |
|
| 43 |
|
| 44 |
Both can be combined for maximum efficiency.
|
|
|
|
| 38 |
|
| 39 |
| Technique | Where it's applied | Savings |
|
| 40 |
|-----------|-------------------|---------|
|
|
|
|
| 41 |
| **RotorQuant KV cache** | At inference time | Reduces attention memory (critical for long context) |
|
| 42 |
|
| 43 |
Both can be combined for maximum efficiency.
|