Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ TODO:
|
|
| 11 |
- benchmark qnn llama2 locally
|
| 12 |
- benchmark T-MAC groupsize 128 if needed
|
| 13 |
- test opencl and available qnn pull requests, feasibility for speculative decoding alongside cpu inference
|
|
|
|
|
|
|
| 14 |
|
| 15 |
|
| 16 |
## Model Benchmarks
|
|
|
|
| 11 |
- benchmark qnn llama2 locally
|
| 12 |
- benchmark T-MAC groupsize 128 if needed
|
| 13 |
- test opencl and available qnn pull requests, feasibility for speculative decoding alongside cpu inference
|
| 14 |
+
- overclocking ram with magisk module
|
| 15 |
+
- potentially check standards in quantization: mlc before regression, executorch, qnn
|
| 16 |
|
| 17 |
|
| 18 |
## Model Benchmarks
|