From faf5815cf86e21b47e76cdfb50dc5550c20b825b Mon Sep 17 00:00:00 2001
From: haic0 <149741444+haic0@users.noreply.github.com>
Date: Thu, 23 Oct 2025 22:32:37 +0800
Subject: [PATCH 1/2] Create AMD-Qwen3-Next-Usage.md

---
 Qwen/AMD/AMD-Qwen3-Next-Usage.md | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 Qwen/AMD/AMD-Qwen3-Next-Usage.md

diff --git a/Qwen/AMD/AMD-Qwen3-Next-Usage.md b/Qwen/AMD/AMD-Qwen3-Next-Usage.md
new file mode 100644
index 00000000..e6a9a818
--- /dev/null
+++ b/Qwen/AMD/AMD-Qwen3-Next-Usage.md
@@ -0,0 +1,30 @@
+#### Step by Step Guide
+Please follow the steps here to install and run Qwen3-Next-80B-A3B-Instruct models on AMD MI300X GPU.
+#### Step 1
+Pull the latest vllm docker:
+```shell
+docker pull rocm/vllm-dev:nightly
+```
+Launch the Rocm-vllm docker: 
+```shell
+docker run -d -it --ipc=host --network=host --privileged --cap-add=CAP_SYS_ADMIN --device=/dev/kfd --device=/dev/dri --device=/dev/mem --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /:/work -e SHELL=/bin/bash  --name Qwen3-next rocm/vllm-dev:nightly
+```
+#### Step 2
+  Huggingface login
+```shell
+   huggingface-cli login 
+```   
+#### Step 3
+##### FP8
+
+Run the vllm online serving
+Sample Command
+```shell
+VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --tensor-parallel-size 4 --max-model-len 32768  --no-enable-prefix-caching 
+```
+#### Step 4 
+Open a new terminal, enter into the running docker and run the following benchmark script.
+```shell
+docker exec -it Qwen3-next /bin/bash 
+python3 /vllm-workspace/benchmarks/benchmark_serving.py --model Qwen/Qwen3-Next-80B-A3B-Instruct --dataset-name random --ignore-eos --num-prompts 500  --max-concurrency 128 --random-input-len 3200 --random-output-len 800  --percentile-metrics ttft,tpot,itl,e2el
+```

From 70cfa887804725180016453b5a4a8b06f847e863 Mon Sep 17 00:00:00 2001
From: haic0 <149741444+haic0@users.noreply.github.com>
Date: Mon, 26 Jan 2026 22:45:46 +0800
Subject: [PATCH 2/2] Update AMD-Qwen3-Next-Usage.md for AMD

---
 Qwen/AMD/AMD-Qwen3-Next-Usage.md | 48 +++++++++++++++++++++++---------
 1 file changed, 35 insertions(+), 13 deletions(-)

diff --git a/Qwen/AMD/AMD-Qwen3-Next-Usage.md b/Qwen/AMD/AMD-Qwen3-Next-Usage.md
index e6a9a818..cc2c4296 100644
--- a/Qwen/AMD/AMD-Qwen3-Next-Usage.md
+++ b/Qwen/AMD/AMD-Qwen3-Next-Usage.md
@@ -1,30 +1,52 @@
+## AMD GPU Support
+Recommended approaches by hardware type are:
+
+
+MI300X/MI325X/MI355X  with fp8: Use FP8 checkpoint for optimal memory efficiency.
+
+- **MI300X/MI325X/MI355X with `fp8`**: Use FP8 checkpoint for optimal memory efficiency.
+- **MI300X/MI325X/MI355X with `bfloat16`**
+  
 #### Step by Step Guide
 Please follow the steps here to install and run Qwen3-Next-80B-A3B-Instruct models on AMD MI300X GPU.
 #### Step 1
 Pull the latest vllm docker:
 ```shell
-docker pull rocm/vllm-dev:nightly
+docker pull vllm/vllm-openai-rocm:v0.14.1
 ```
 Launch the Rocm-vllm docker: 
 ```shell
-docker run -d -it --ipc=host --network=host --privileged --cap-add=CAP_SYS_ADMIN --device=/dev/kfd --device=/dev/dri --device=/dev/mem --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /:/work -e SHELL=/bin/bash  --name Qwen3-next rocm/vllm-dev:nightly
+docker run -d -it --ipc=host --network=host --privileged --cap-add=CAP_SYS_ADMIN --device=/dev/kfd --device=/dev/dri --device=/dev/mem --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /:/work -e SHELL=/bin/bash  --name Qwen3-next vllm/vllm-openai-rocm:v0.14.1
 ```
-#### Step 2
-  Huggingface login
+### Step 2: Log in to Hugging Face
+Log in to your Hugging Face account:
 ```shell
-   huggingface-cli login 
-```   
-#### Step 3
-##### FP8
+hf auth login
+```
+
+### Step 3: Start the vLLM server
 
 Run the vllm online serving
-Sample Command
+### BF16 
 ```shell
 VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --tensor-parallel-size 4 --max-model-len 32768  --no-enable-prefix-caching 
 ```
-#### Step 4 
-Open a new terminal, enter into the running docker and run the following benchmark script.
+### FP8
 ```shell
-docker exec -it Qwen3-next /bin/bash 
-python3 /vllm-workspace/benchmarks/benchmark_serving.py --model Qwen/Qwen3-Next-80B-A3B-Instruct --dataset-name random --ignore-eos --num-prompts 500  --max-concurrency 128 --random-input-len 3200 --random-output-len 800  --percentile-metrics ttft,tpot,itl,e2el
+VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct-FP8 --tensor-parallel-size 4 --max-model-len 32768  --no-enable-prefix-caching 
 ```
+#### Step 4 Run Benchmark
+
+Open a new terminal and run the following command to execute the benchmark script inside the container.
+```shell
+docker exec -it Qwen3-next vllm bench serve \
+  --model "Qwen/Qwen3-Next-80B-A3B-Instruct" \
+  --dataset-name random \
+  --random-input-len 8192 \
+  --random-output-len 1024 \
+  --request-rate 10000 \
+  --num-prompts 16 \
+  --ignore-eos \
+  --trust-remote-code 
+```
+