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 (34.54 GB needed), around 1.5x 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 (34.54 GB needed), around 1.7x speedup and little to no accuracy impact on H100.
 
 # Inference with vLLM
 ```Shell
@@ -164,8 +164,8 @@ lm_eval --model hf --model_args pretrained=$MODEL --tasks mmlu --device cuda:0 -
 
 | Memory (tested on H100)          |                |                               |
 |----------------------------------|----------------|-------------------------------|
-|                                  | Qwen3-32B      | Qwen3-32B-FP8            | 
-| Peak Memory                      | 65.72 GB       | 34.54 GB (47.44% reduction)   |
+|                                  | Qwen3-32B      | Qwen3-32B-FP8                 | 
+| Peak Memory                      | 65.63 GB       | 34.71 GB (47.1% reduction)    |
 
 <details>
 <summary> Reproduce Peak Memory Usage Results </summary>
@@ -232,9 +232,9 @@ print(f"Peak Memory Usage: {mem:.02f} GB")
 
 | Benchmark  (Tested on H100)      |                |                               |
 |----------------------------------|----------------|-------------------------------|
-|                                  | Qwen3-32B      | Qwen3-32B-FP8            | 
-| latency (batch_size=1)           | 9.1s           | 5.77s (1.58x speedup)         |
-| latency (batch_size=128)         | 12.45s         | 8.40s (1.48x speedup)         |
+|                                  | Qwen3-32B      | Qwen3-32B-FP8                 | 
+| latency (batch_size=1)           | 8.93s          | 5.16s (1.73x speedup)         |
+| latency (batch_size=256)         | 33.85s         | 16.15s (2.10x speedup)        |
 
 <details>
 <summary> Reproduce latency benchmarks </summary>