Update README.md

README.md

@@ -14,16 +14,24 @@ base_model:
 - **PyTorch**: 2.9.0
 - **Operating System(s):** Linux
 - **Inference Engine:** [vLLM](https://docs.vllm.ai/en/latest/)
-- **Model Optimizer:** [AMD-Quark (v0.10)](https://quark.docs.amd.com/latest/index.html)
-  - **Weight quantization:** OCP MXFP4, Static
-  - **Activation quantization:** FP8, Dynamic
+- **Model Optimizer:** [AMD-Quark (v0.11)](https://quark.docs.amd.com/latest/index.html)
+  - **moe**
+    - **Weight quantization:** OCP MXFP4, Static
+    - **Activation quantization:** FP8, Dynamic
+  - **qkvo**
+    - **Weight quantization:** FP8 per_channel, Static
+    - **Activation quantization:** FP8 per_token, Dynamic
+  - **kv-cache**
+    - **Output quantization:** FP8, Static
+  - **softmax**
+    - **Output quantization:** FP8, Static
 - **Calibration Dataset:** [Pile](https://huggingface.co/datasets/mit-han-lab/pile-val-backup)
 
-This model was built with gpt-oss-120b model by applying [AMD-Quark](https://quark.docs.amd.com/latest/index.html) for mixed MXFP4-FP8 quantization.
+This model was built with gpt-oss-120b model by applying [AMD-Quark (v0.11)](https://quark.docs.amd.com/latest/index.html) for mixed MXFP4-FP8 quantization.
 
 # Model Quantization
 
-The model was quantized from [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) using [AMD-Quark](https://quark.docs.amd.com/latest/index.html). The weights are quantized MXFP4 and activations were quantized to FP8. 
+The model was quantized from [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) using [AMD-Quark (v0.11)](https://quark.docs.amd.com/latest/index.html). The weights are quantized MXFP4 and activations were quantized to FP8. 
 
 **Quantization scripts:**
 ```
@@ -92,10 +100,16 @@ The model was evaluated on AIME25 and GPQA Diamond benchmarks with `medium` reas
 ### Reproduction
 
 The results of GPQA Diamond and AIME25 were obtained using [gpt_oss.evals](https://github.com/openai/gpt-oss/tree/main/gpt_oss/evals) with `medium` effort setting, and vLLM docker `rocm/vllm-dev:mxfp4_fp8_gpt_oss_native_20251226`.
-This version od vllm is 
+vLLM and Aiter are already compiled and pre-installed in the Docker image, there is no need to download or install them again.
 
 #### Launching server
+
 ```
+export VLLM_USE_AITER_UNIFIED_ATTENTION=1
+export VLLM_ROCM_USE_AITER_MHA=0
+export VLLM_ROCM_USE_AITER_FUSED_MOE_A16W4=0
+export USE_Q_SCALE=1
+
 vllm serve amd/gpt-oss-120b-w-mxfp4-a-fp8-qkvo-ptpc-fp8-kv-fp8-fp8attn \
   --tensor_parallel_size 2 \
   --gpu-memory-utilization 0.90 \
@@ -106,6 +120,8 @@ vllm serve amd/gpt-oss-120b-w-mxfp4-a-fp8-qkvo-ptpc-fp8-kv-fp8-fp8attn \
 
 #### Evaluating model in a new terminal
 ```
+export OPENAI_API_KEY="EMPTY"
+
 python -m gpt_oss.evals --model amd/gpt-oss-120b-w-mxfp4-a-fp8-qkvo-ptpc-fp8-kv-fp8-fp8attn --eval aime25,gpqa --reasoning-effort medium --n-threads 128
 ```