Update README.md
Browse files
README.md
CHANGED
|
@@ -141,6 +141,7 @@ asyncio.run(
|
|
| 141 |
|
| 142 |
Planned improvements:
|
| 143 |
|
|
|
|
| 144 |
- Huggingface transformers generation
|
| 145 |
- vLLM CLI benchmarking for detailed latency evaluation
|
| 146 |
- `lm-eval-harness` integration for detailed accuracy evaluation
|
|
|
|
| 141 |
|
| 142 |
Planned improvements:
|
| 143 |
|
| 144 |
+
- Advanced mixed precision quantization
|
| 145 |
- Huggingface transformers generation
|
| 146 |
- vLLM CLI benchmarking for detailed latency evaluation
|
| 147 |
- `lm-eval-harness` integration for detailed accuracy evaluation
|