Update README.md

README.md

@@ -13,7 +13,7 @@ base_model:
 pipeline_tag: text-generation
 ---
 
-[Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) model quantized with [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao) float8 dynamic activation and float8 weight quantization (per row granularity), by PyTorch team. Use it directly, or serve using [vLLM](https://docs.vllm.ai/en/latest/) with 47% VRAM reduction, around 50% speedup and little to no accuracy impact on H100.
+[Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) model quantized with [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao) float8 dynamic activation and float8 weight quantization (per row granularity), by PyTorch team. Use it directly, or serve using [vLLM](https://docs.vllm.ai/en/latest/) with 47% VRAM reduction, around 1.5x speedup and little to no accuracy impact on H100.
 
 # Inference with vLLM
 ```Shell
@@ -233,8 +233,8 @@ print(f"Peak Memory Usage: {mem:.02f} GB")
 | Benchmark  (Tested on H100)      |                |                               |
 |----------------------------------|----------------|-------------------------------|
 |                                  | Qwen3-32B      | Qwen3-32B-float8dq            | 
-| latency (batch_size=1)           | 9.1s           | 5.77s (57.7% speedup)         |
-| latency (batch_size=128)         | 12.45s         | 8.40s (48% speedup)           |
+| latency (batch_size=1)           | 9.1s           | 5.77s (1.58x speedup)         |
+| latency (batch_size=128)         | 12.45s         | 8.40s (1.48x speedup)         |
 
 <details>
 <summary> Reproduce latency benchmarks </summary>