[docs/7.1.1] Publish vLLM and xDiT doc updates (#5787)

* vLLM inference benchmark 1210 (#5776) * Archive previous ver fix anchors * Update vllm.rst and data yaml for 20251210 (cherry picked from commit 1b4f25733d) * xDiT diffusion inference v25.12 documentation update (#5786) * Add xdit-diffusion ROCm docs page. * Update template formatting and fix sphinx warnings * Add System Validation section. * Add sw component versions/commits. * Update to use latest v25.10 image instead of v25.9 * Update commands and add FLUX instructions. * Update Flux instructions. Change image tag. Describe as diffusion inference instead of specifically video. * git rm xdit-video-diffusion.rst * Docs for v25.12 * Add hyperlinks to components * Command fixes * -Diffusers suffix * Simplify yaml file and cleanup main rst page. * Spelling, added 'js' * fix merge conflict fix --------- Co-authored-by: Kristoffer <kristoffer.torp@amd.com> (cherry picked from commit 459283da3c) --------- Co-authored-by: Kristoffer <kristoffer.torp@amd.com>
2026-01-11 07:38:17 -05:00 · 2025-12-17 10:28:30 -05:00
parent e5cebe7b4e
commit 94de66ef3f
11 changed files with 994 additions and 188 deletions
--- a/.wordlist.txt
+++ b/.wordlist.txt
@@ -264,6 +264,7 @@ Ioffe
 JAX's
 JAXLIB
 Jinja
+js
 JSON
 Jupyter
 KFD
--- a/docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.11.1_20251103-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.11.1_20251103-benchmark-models.yaml
@@ -0,0 +1,316 @@
+dockers:
+  - pull_tag: rocm/vllm:rocm7.0.0_vllm_0.11.1_20251103
+    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.11.1_20251103/images/sha256-8d60429043d4d00958da46039a1de0d9b82df814d45da482497eef26a6076506
+    components:
+      ROCm: 7.0.0
+      vLLM: 0.11.1 (0.11.1rc2.dev141+g38f225c2a.rocm700)
+      PyTorch: 2.9.0a0+git1c57644
+      hipBLASLt: 1.0.0
+    dockerfile:
+      commit: 38f225c2abeadc04c2cc398814c2f53ea02c3c72
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 2 70B
+        mad_tag: pyt_vllm_llama-2-70b
+        model_repo: meta-llama/Llama-2-70b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 4096
+          max_model_len: 4096
+      - model: Llama 3.1 8B
+        mad_tag: pyt_vllm_llama-3.1-8b
+        model_repo: meta-llama/Llama-3.1-8B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 8B FP8
+        mad_tag: pyt_vllm_llama-3.1-8b_fp8
+        model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
+        precision: float8
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 405B
+        mad_tag: pyt_vllm_llama-3.1-405b
+        model_repo: meta-llama/Llama-3.1-405B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 405B FP8
+        mad_tag: pyt_vllm_llama-3.1-405b_fp8
+        model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 405B MXFP4
+        mad_tag: pyt_vllm_llama-3.1-405b_fp4
+        model_repo: amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        precision: float4
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B
+        mad_tag: pyt_vllm_llama-3.3-70b
+        model_repo: meta-llama/Llama-3.3-70B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B FP8
+        mad_tag: pyt_vllm_llama-3.3-70b_fp8
+        model_repo: amd/Llama-3.3-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B MXFP4
+        mad_tag: pyt_vllm_llama-3.3-70b_fp4
+        model_repo: amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+        precision: float4
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 4 Scout 17Bx16E
+        mad_tag: pyt_vllm_llama-4-scout-17b-16e
+        model_repo: meta-llama/Llama-4-Scout-17B-16E-Instruct
+        url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Llama 4 Maverick 17Bx128E
+        mad_tag: pyt_vllm_llama-4-maverick-17b-128e
+        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Llama 4 Maverick 17Bx128E FP8
+        mad_tag: pyt_vllm_llama-4-maverick-17b-128e_fp8
+        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek R1 0528 FP8
+        mad_tag: pyt_vllm_deepseek-r1
+        model_repo: deepseek-ai/DeepSeek-R1-0528
+        url: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_seqs: 1024
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+  - group: OpenAI GPT OSS
+    tag: gpt-oss
+    models:
+      - model: GPT OSS 20B
+        mad_tag: pyt_vllm_gpt-oss-20b
+        model_repo: openai/gpt-oss-20b
+        url: https://huggingface.co/openai/gpt-oss-20b
+        precision: bfloat16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 8192
+          max_model_len: 8192
+      - model: GPT OSS 120B
+        mad_tag: pyt_vllm_gpt-oss-120b
+        model_repo: openai/gpt-oss-120b
+        url: https://huggingface.co/openai/gpt-oss-120b
+        precision: bfloat16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 8192
+          max_model_len: 8192
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral MoE 8x7B
+        mad_tag: pyt_vllm_mixtral-8x7b
+        model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Mixtral MoE 8x7B FP8
+        mad_tag: pyt_vllm_mixtral-8x7b_fp8
+        model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Mixtral MoE 8x22B
+        mad_tag: pyt_vllm_mixtral-8x22b
+        model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 65536
+          max_model_len: 8192
+      - model: Mixtral MoE 8x22B FP8
+        mad_tag: pyt_vllm_mixtral-8x22b_fp8
+        model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 65536
+          max_model_len: 8192
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen3 8B
+        mad_tag: pyt_vllm_qwen3-8b
+        model_repo: Qwen/Qwen3-8B
+        url: https://huggingface.co/Qwen/Qwen3-8B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 32B
+        mad_tag: pyt_vllm_qwen3-32b
+        model_repo: Qwen/Qwen3-32b
+        url: https://huggingface.co/Qwen/Qwen3-32B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 30B A3B
+        mad_tag: pyt_vllm_qwen3-30b-a3b
+        model_repo: Qwen/Qwen3-30B-A3B
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 30B A3B FP8
+        mad_tag: pyt_vllm_qwen3-30b-a3b_fp8
+        model_repo: Qwen/Qwen3-30B-A3B-FP8
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 235B A22B
+        mad_tag: pyt_vllm_qwen3-235b-a22b
+        model_repo: Qwen/Qwen3-235B-A22B
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 235B A22B FP8
+        mad_tag: pyt_vllm_qwen3-235b-a22b_fp8
+        model_repo: Qwen/Qwen3-235B-A22B-FP8
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+  - group: Microsoft Phi
+    tag: phi
+    models:
+      - model: Phi-4
+        mad_tag: pyt_vllm_phi-4
+        model_repo: microsoft/phi-4
+        url: https://huggingface.co/microsoft/phi-4
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 16384
+          max_model_len: 8192
--- a/docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
@@ -1,13 +1,13 @@
 dockers:
-  - pull_tag: rocm/vllm:rocm7.0.0_vllm_0.11.1_20251103
-    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.11.1_20251103/images/sha256-8d60429043d4d00958da46039a1de0d9b82df814d45da482497eef26a6076506
+  - pull_tag: rocm/vllm:rocm7.0.0_vllm_0.11.2_20251210
+    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.11.2_20251210/images/sha256-e7f02dd2ce3824959658bc0391296f6158638e3ebce164f6c019c4eca8150ec7
    components:
      ROCm: 7.0.0
-      vLLM: 0.11.1 (0.11.1rc2.dev141+g38f225c2a.rocm700)
+      vLLM: 0.11.2 (0.11.2.dev673+g839868462.rocm700)
      PyTorch: 2.9.0a0+git1c57644
      hipBLASLt: 1.0.0
    dockerfile:
-      commit: 38f225c2abeadc04c2cc398814c2f53ea02c3c72
+      commit: 8398684622109c806a35d660647060b0b9910663
 model_groups:
  - group: Meta Llama
    tag: llama
--- a/docs/data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
@@ -1,109 +1,91 @@
-xdit_diffusion_inference:
-  docker:
-    - version: v25-11
-      pull_tag: rocm/pytorch-xdit:v25.11
-      docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
-      ROCm: 7.10.0
-      supported_models:
-        - group: Hunyuan Video
-          models:
-            - Hunyuan Video
-        - group: Wan-AI
-          models:
-            - Wan2.1
-            - Wan2.2
-        - group: FLUX
-          models:
-            - FLUX.1
-      whats_new:
-        - "Minor bug fixes and clarifications to READMEs."
-        - "Bumps TheRock, AITER, Diffusers, xDiT versions."
-        - "Changes Aiter rounding mode for faster gfx942 FWD Attention."
-      components:
-        TheRock: 3e3f834
-        rccl: d23d18f
-        composable_kernel: 2570462
-        rocm-libraries: 0588f07
-        rocm-systems: 473025a
-        torch: 73adac
-        torchvision: f5c6c2e
-        triton: 7416ffc
-        accelerate: 34c1779
-        aiter: de14bec
-        diffusers: 40528e9
-        xfuser: 83978b5
-        yunchang: 2c9b712
-
-    - version: v25-10
-      pull_tag: rocm/pytorch-xdit:v25.10
-      docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
-      ROCm: 7.9.0
-      supported_models:
-        - group: Hunyuan Video
-          models:
-            - Hunyuan Video
-        - group: Wan-AI
-          models:
-            - Wan2.1
-            - Wan2.2
-        - group: FLUX
-          models:
-            - FLUX.1
-      whats_new:
-        - "First official xDiT Docker Release for Diffusion Inference."
-        - "Supports gfx942 and gfx950 series (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X)."
-        - "Support Wan 2.1, Wan 2.2, HunyuanVideo and Flux workloads."
-      components:
-        TheRock: 7afbe45
-        rccl: 9b04b2a
-        composable_kernel: b7a806f
-        rocm-libraries: f104555
-        rocm-systems: 25922d0
-        torch: 2.10.0a0+gite9c9017
-        torchvision: 0.22.0a0+966da7e
-        triton: 3.5.0+git52e49c12
-        accelerate: 1.11.0.dev0
-        aiter: 0.1.5.post4.dev20+ga25e55e79
-        diffusers: 0.36.0.dev0
-        xfuser: 0.4.4
-        yunchang: 0.6.3.post1
-
-  model_groups:
+docker:
+  pull_tag: rocm/pytorch-xdit:v25.12
+  docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
+  ROCm: 7.10.0
+  whats_new:
+      - "Adds T2V and TI2V support for Wan models."
+      - "Adds support for SD-3.5 T2I model."
+  components:
+    TheRock: 
+      version: 3e3f834
+      url: https://github.com/ROCm/TheRock
+    rccl:
+      version: d23d18f
+      url: https://github.com/ROCm/rccl
+    composable_kernel:
+      version: 2570462
+      url: https://github.com/ROCm/composable_kernel
+    rocm-libraries:
+      version: 0588f07
+      url: https://github.com/ROCm/rocm-libraries
+    rocm-systems:
+      version: 473025a
+      url: https://github.com/ROCm/rocm-systems
+    torch:
+      version: 73adac
+      url: https://github.com/pytorch/pytorch
+    torchvision:
+      version: f5c6c2e
+      url: https://github.com/pytorch/vision
+    triton:
+      version: 7416ffc
+      url: https://github.com/triton-lang/triton
+    accelerate:
+      version: 34c1779
+      url: https://github.com/huggingface/accelerate
+    aiter:
+      version: de14bec
+      url: https://github.com/ROCm/aiter
+    diffusers:
+      version: 40528e9
+      url: https://github.com/huggingface/diffusers
+    xfuser:
+      version: ccba9d5
+      url: https://github.com/xdit-project/xDiT
+    yunchang:
+      version: 2c9b712
+      url: https://github.com/feifeibear/long-context-attention
+  supported_models:
    - group: Hunyuan Video
-      tag: hunyuan
+      js_tag: hunyuan
      models:
        - model: Hunyuan Video
-          page_tag: hunyuan_tag
-          model_name: hunyuanvideo
          model_repo: tencent/HunyuanVideo
          revision: refs/pr/18
          url: https://huggingface.co/tencent/HunyuanVideo
          github: https://github.com/Tencent-Hunyuan/HunyuanVideo
          mad_tag: pyt_xdit_hunyuanvideo
+          js_tag: hunyuan_tag
    - group: Wan-AI
-      tag: wan
+      js_tag: wan
      models:
        - model: Wan2.1
-          page_tag: wan_21_tag
-          model_name: wan2_1-i2v-14b-720p
-          model_repo: Wan-AI/Wan2.1-I2V-14B-720P
-          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P
+          model_repo: Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
          github: https://github.com/Wan-Video/Wan2.1
          mad_tag: pyt_xdit_wan_2_1
+          js_tag: wan_21_tag
        - model: Wan2.2
-          page_tag: wan_22_tag
-          model_name: wan2_2-i2v-a14b
-          model_repo: Wan-AI/Wan2.2-I2V-A14B
-          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B
+          model_repo: Wan-AI/Wan2.2-I2V-A14B-Diffusers
+          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers
          github: https://github.com/Wan-Video/Wan2.2
          mad_tag: pyt_xdit_wan_2_2
+          js_tag: wan_22_tag
    - group: FLUX
-      tag: flux
+      js_tag: flux
      models:
        - model: FLUX.1
-          page_tag: flux_1_tag
-          model_name: FLUX.1-dev
          model_repo: black-forest-labs/FLUX.1-dev
          url: https://huggingface.co/black-forest-labs/FLUX.1-dev
          github: https://github.com/black-forest-labs/flux
          mad_tag: pyt_xdit_flux
+          js_tag: flux_1_tag
+    - group: Stable Diffusion
+      js_tag: stablediffusion
+      models:
+        - model: stable-diffusion-3.5-large
+          model_repo: stabilityai/stable-diffusion-3.5-large
+          url: https://huggingface.co/stabilityai/stable-diffusion-3.5-large
+          github: https://github.com/Stability-AI/sd3.5
+          mad_tag: pyt_xdit_sd_3_5
+          js_tag: stable_diffusion_3_5_large_tag
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.11.1-20251103.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.11.1-20251103.rst
@@ -0,0 +1,472 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the ROCm vLLM Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker-1103:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.11.1_20251103-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+
+   The `ROCm vLLM Docker <{{ docker.docker_hub_url }}>`_ image offers a
+   prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on AMD Instinct™ MI355X, MI350X, MI325X and MI300X
+   GPUs. This ROCm vLLM Docker image integrates vLLM and PyTorch tailored
+   specifically for AMD data center GPUs and includes the following components:
+
+   .. tab-set::
+
+      .. tab-item:: {{ docker.pull_tag }}
+
+         .. list-table::
+            :header-rows: 1
+
+            * - Software component
+              - Version
+
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}
+
+With this Docker image, you can quickly test the :ref:`expected
+inference performance numbers <vllm-benchmark-performance-measurements-1103>` for
+AMD Instinct GPUs.
+
+What's new
+==========
+
+The following is summary of notable changes since the :doc:`previous ROCm/vLLM Docker release <vllm-history>`.
+
+* Enabled :ref:`AITER <vllm-optimization-aiter-switches>` by default.
+
+* Fixed ``rms_norm`` segfault issue with Qwen 3 235B.
+
+* Known performance degradation on Llama 4 models due to `an upstream vLLM issue <https://github.com/vllm-project/vllm/issues/26320>`_.
+
+.. _vllm-benchmark-supported-models-1103:
+
+Supported models
+================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.11.1_20251103-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+
+   .. _vllm-benchmark-available-models-1103:
+
+   The following models are supported for inference performance benchmarking
+   with vLLM and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started. MXFP4 models
+   are only supported on MI355X and MI350X GPUs.
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+   .. _vllm-benchmark-vllm-1103:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.mad_tag }}
+
+
+      {% if model.precision == "float4" %}
+      .. important::
+
+         MXFP4 is supported only on MI355X and MI350X GPUs.
+      {% endif %}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
+         Some models require access authorization prior to use via an external license agreement through a third party.
+      {% if model.precision == "float8" and model.model_repo.startswith("amd") %}
+         This model uses FP8 quantization via `AMD Quark <https://quark.docs.amd.com/latest/>`__ for efficient inference on AMD GPUs.
+      {% endif %}
+      {% if model.precision == "float4" and model.model_repo.startswith("amd") %}
+         This model uses FP4 quantization via `AMD Quark <https://quark.docs.amd.com/latest/>`__ for efficient inference on AMD GPUs.
+      {% endif %}
+
+      {% endfor %}
+   {% endfor %}
+
+.. _vllm-benchmark-performance-measurements-1103:
+
+Performance measurements
+========================
+
+To evaluate performance, the
+`Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+page provides reference throughput and serving measurements for inferencing popular AI models.
+
+.. important::
+
+   The performance data presented in
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+   only reflects the latest version of this inference benchmarking environment.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct GPUs or ROCm software.
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+Pull the Docker image
+=====================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.11.1_20251103-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+
+   Download the `ROCm vLLM Docker image <{{ docker.docker_hub_url }}>`_.
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ docker.pull_tag }}
+
+Benchmarking
+============
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.11.1_20251103-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+
+   Once the setup is complete, choose between two options to reproduce the
+   benchmark results:
+
+   .. _vllm-benchmark-mad-1103:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`vllm-benchmark-supported-models-1103` to switch to another available model.
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. On the host machine, use this command to run the performance benchmark test on
+               the `{{model.model}} <{{ model.url }}>`_ model using one node with the
+               :literal:`{{model.precision}}` data type.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{model.mad_tag}} \
+                      --keep-model-dir \
+                      --live-output
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
+            model are collected in the following paths: ``{{ model.mad_tag }}_throughput.csv``
+            and ``{{ model.mad_tag }}_serving.csv``.
+
+            Although the :ref:`available models
+            <vllm-benchmark-available-models-1103>` are preconfigured to collect
+            offline throughput and online serving performance data, you can
+            also change the benchmarking parameters. See the standalone
+            benchmarking tab for more information.
+
+            {% if model.tunableop %}
+
+            .. note::
+
+               For improved performance, consider enabling :ref:`PyTorch TunableOp <mi300x-tunableop>`.
+               TunableOp automatically explores different implementations and configurations of certain PyTorch
+               operators to find the fastest one for your hardware.
+
+               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled (see
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To enable it, include
+               the ``--tunableop on`` argument in your run.
+
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the
+               performance-collection run.
+
+            {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            The following commands are optimized for {{ model.model }}.
+            See :ref:`vllm-benchmark-supported-models-1103` to switch to another available model.
+
+            .. seealso::
+
+               For more information on configuration, see the `config files
+               <https://github.com/ROCm/MAD/tree/develop/scripts/vllm/configs>`__
+               in the MAD repository. Refer to the `vLLM engine <https://docs.vllm.ai/en/latest/configuration/engine_args.html#engineargs>`__
+               for descriptions of available configuration options
+               and `Benchmarking vLLM <https://github.com/vllm-project/vllm/blob/main/benchmarks/README.md>`__ for
+               additional benchmarking information.
+
+            .. rubric:: Launch the container
+
+            You can run the vLLM benchmark tool independently by starting the
+            `Docker container <{{ docker.docker_hub_url }}>`_ as shown
+            in the following snippet.
+
+            .. code-block:: shell
+
+               docker pull {{ docker.pull_tag }}
+               docker run -it \
+                   --device=/dev/kfd \
+                   --device=/dev/dri \
+                   --group-add video \
+                   --shm-size 16G \
+                   --security-opt seccomp=unconfined \
+                   --security-opt apparmor=unconfined \
+                   --cap-add=SYS_PTRACE \
+                   -v $(pwd):/workspace \
+                   --env HUGGINGFACE_HUB_CACHE=/workspace \
+                   --name test \
+                   {{ docker.pull_tag }}
+
+            .. rubric:: Throughput command
+
+            Use the following command to start the throughput benchmark.
+
+            .. code-block:: shell
+
+               model={{ model.model_repo }}
+               tp={{ model.config.tp }}
+               num_prompts={{ model.config.num_prompts | default(1024) }}
+               in={{ model.config.in | default(128) }}
+               out={{ model.config.in | default(128) }}
+               dtype={{ model.config.dtype | default("auto") }}
+               kv_cache_dtype={{ model.config.kv_cache_dtype }}
+               max_num_seqs={{ model.config.max_num_seqs | default(1024) }}
+               max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
+               max_model_len={{ model.config.max_model_len }}
+
+               vllm bench throughput --model $model \
+                   -tp $tp \
+                   --num-prompts $num_prompts \
+                   --input-len $in \
+                   --output-len $out \
+                   --dtype $dtype \
+                   --kv-cache-dtype $kv_cache_dtype \
+                   --max-num-seqs $max_num_seqs \
+                   --max-num-batched-tokens $max_num_batched_tokens \
+                   --max-model-len $max_model_len \
+                   --trust-remote-code \
+                   --output-json ${model}_throughput.json \
+                   --gpu-memory-utilization {{ model.config.gpu_memory_utilization | default(0.9) }}
+
+            .. rubric:: Serving command
+
+            1. Start the server using the following command:
+
+               .. code-block:: shell
+
+                  model={{ model.model_repo }}
+                  tp={{ model.config.tp }}
+                  dtype={{ model.config.dtype }}
+                  kv_cache_dtype={{ model.config.kv_cache_dtype }}
+                  max_num_seqs=256
+                  max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
+                  max_model_len={{ model.config.max_model_len }}
+
+                  vllm serve $model \
+                      -tp $tp \
+                      --dtype $dtype \
+                      --kv-cache-dtype $kv_cache_dtype \
+                      --max-num-seqs $max_num_seqs \
+                      --max-num-batched-tokens $max_num_batched_tokens \
+                      --max-model-len $max_model_len \
+                      --no-enable-prefix-caching \
+                      --swap-space 16 \
+                      --disable-log-requests \
+                      --trust-remote-code \
+                      --gpu-memory-utilization 0.9
+
+               Wait until the model has loaded and the server is ready to accept requests.
+
+            2. On another terminal on the same machine, run the benchmark:
+
+               .. code-block:: shell
+
+                  # Connect to the container
+                  docker exec -it test bash
+
+                  # Wait for the server to start
+                  until curl -s http://localhost:8000/v1/models; do sleep 30; done
+
+                  # Run the benchmark
+                  model={{ model.model_repo }}
+                  max_concurrency=1
+                  num_prompts=10
+                  in=128
+                  out=128
+                  vllm bench serve --model $model \
+                      --percentile-metrics "ttft,tpot,itl,e2el" \
+                      --dataset-name random \
+                      --ignore-eos \
+                      --max-concurrency $max_concurrency \
+                      --num-prompts $num_prompts \
+                      --random-input-len $in \
+                      --random-output-len $out \
+                      --trust-remote-code \
+                      --save-result \
+                      --result-filename ${model}_serving.json
+
+            .. note::
+
+               For improved performance with certain Mixture of Experts models, such as Mixtral 8x22B,
+               try adding ``export VLLM_ROCM_USE_AITER=1`` to your commands.
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block::
+
+                  OSError: You are trying to access a gated repo.
+
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Advanced usage
+==============
+
+For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
+see the developer's guide at `<https://github.com/ROCm/vllm/blob/documentation/docs/dev-docker/README.md>`__.
+
+.. note::
+
+   If you’re using this Docker image on other AMD GPUs such as the AMD Instinct MI200 Series or Radeon, add ``export VLLM_ROCM_USE_AITER=0`` to your command, since AITER is only supported on gfx942 and gfx950 architectures.
+
+Reproducing the Docker image
+----------------------------
+
+To reproduce this ROCm-enabled vLLM Docker image release, follow these steps:
+
+1. Clone the `vLLM repository <https://github.com/vllm-project/vllm>`__.
+
+   .. code-block:: shell
+
+      git clone https://github.com/vllm-project/vllm.git
+      cd vllm
+
+2. Use the following command to build the image directly from the specified commit.
+
+   .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.11.1_20251103-benchmark-models.yaml
+
+      {% set docker = data.dockers[0] %}
+      .. code-block:: shell
+
+         docker build -f docker/Dockerfile.rocm \
+             --build-arg REMOTE_VLLM=1 \
+             --build-arg VLLM_REPO=https://github.com/ROCm/vllm \
+             --build-arg VLLM_BRANCH="{{ docker.dockerfile.commit }}" \
+             -t vllm-rocm .
+
+   .. tip::
+
+      Replace ``vllm-rocm`` with your desired image tag.
+
+Further reading
+===============
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+  a brief introduction to vLLM and optimization strategies.
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-history.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-history.rst
@@ -16,15 +16,23 @@ previous releases of the ``ROCm/vllm`` Docker image on `Docker Hub <https://hub.
     - Components
     - Resources

-   * - ``rocm/vllm:rocm7.0.0_vllm_0.11.1_20251024``
-       (latest)
+   * - ``rocm/vllm:rocm7.0.0_vllm_0.11.2_20251210``
+     -
+       * ROCm 7.0.0
+       * vLLM 0.11.2
+       * PyTorch 2.9.0
+     -
+       * :doc:`Documentation <../vllm>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.11.2_20251210/images/sha256-e7f02dd2ce3824959658bc0391296f6158638e3ebce164f6c019c4eca8150ec7>`__
+
+   * - ``rocm/vllm:rocm7.0.0_vllm_0.11.1_20251103``
     -
       * ROCm 7.0.0
       * vLLM 0.11.1
       * PyTorch 2.9.0
     -
-       * :doc:`Documentation <../vllm>`
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.10.2_20251006/images/sha256-94fd001964e1cf55c3224a445b1fb5be31a7dac302315255db8422d813edd7f5>`__
+       * :doc:`Documentation <vllm_0.11.1-20251103>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.11.1_20251103/images/sha256-8d60429043d4d00958da46039a1de0d9b82df814d45da482497eef26a6076506>`__

   * - ``rocm/vllm:rocm7.0.0_vllm_0.10.2_20251006``
     -
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.10.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.10.rst
@@ -1,3 +1,5 @@
+:orphan:
+
 .. meta::
   :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using
                 prebuilt and optimized docker images.
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-history.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-history.rst
@@ -17,7 +17,7 @@ benchmarking, see the version-specific documentation.

   * - ``rocm/pytorch-xdit:v25.11`` (latest)
     - 
-       * ROCm 7.10.0 preview
+       * `ROCm 7.10.0 preview <https://rocm.docs.amd.com/en/7.10.0-preview/about/release-notes.html>`__
       * TheRock 3e3f834
       * rccl d23d18f
       * composable_kernel 2570462
@@ -37,7 +37,7 @@ benchmarking, see the version-specific documentation.

   * - ``rocm/pytorch-xdit:v25.10``
     - 
-       * ROCm 7.9.0 preview
+       * `ROCm 7.9.0 preview <https://rocm.docs.amd.com/en/7.9.0-preview/about/release-notes.html>`__
       * TheRock 7afbe45
       * rccl 9b04b2a
       * composable_kernel b7a806f
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
@@ -6,7 +6,7 @@
 vLLM inference performance testing
 **********************************

-.. _vllm-benchmark-unified-docker-1024:
+.. _vllm-benchmark-unified-docker-1210:

 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml

@@ -34,21 +34,18 @@ vLLM inference performance testing
            {% endfor %}

 With this Docker image, you can quickly test the :ref:`expected
-inference performance numbers <vllm-benchmark-performance-measurements-1024>` for
+inference performance numbers <vllm-benchmark-performance-measurements-1210>` for
 AMD Instinct GPUs.

 What's new
 ==========

-The following is summary of notable changes since the :doc:`previous ROCm/vLLM Docker release <previous-versions/vllm-history>`.
+The following is summary of notable changes since the :doc:`previous ROCm/vLLM
+Docker release <previous-versions/vllm-history>`.

-* Enabled :ref:`AITER <vllm-optimization-aiter-switches>` by default.
+- Improved performance on Llama 3 MXFP4 through AITER optimizations and improved kernel fusion.

-* Fixed ``rms_norm`` segfault issue with Qwen 3 235B.
-
-* Known performance degradation on Llama 4 models due to `an upstream vLLM issue <https://github.com/vllm-project/vllm/issues/26320>`_.
-
-.. _vllm-benchmark-supported-models-1024:
+.. _vllm-benchmark-supported-models-1210:

 Supported models
 ================
@@ -58,7 +55,7 @@ Supported models
   {% set docker = data.dockers[0] %}
   {% set model_groups = data.model_groups %}

-   .. _vllm-benchmark-available-models-1024:
+   .. _vllm-benchmark-available-models-1210:

   The following models are supported for inference performance benchmarking
   with vLLM and ROCm. Some instructions, commands, and recommendations in this
@@ -94,7 +91,7 @@ Supported models
         </div>
      </div>

-   .. _vllm-benchmark-vllm-1024:
+   .. _vllm-benchmark-vllm-1210:

   {% for model_group in model_groups %}
      {% for model in model_group.models %}
@@ -108,6 +105,15 @@ Supported models
         MXFP4 is supported only on MI355X and MI350X GPUs.
      {% endif %}

+      {% if model.mad_tag in ["pyt_vllm_mixtral-8x7b", "pyt_vllm_mixtral-8x7b_fp8", "pyt_vllm_mixtral-8x22b", "pyt_vllm_mixtral-8x22b_fp8", "pyt_vllm_deepseek-r1"] %}
+      .. caution::
+
+         There is a known regression with AITER for MoE models such as Mixtral and
+         DeepSeek-R1. Consider using the :doc:`previous release
+         <previous-versions/vllm-0.11.1-20251103>`
+         ``rocm/vllm:rocm7.0.0_vllm_0.11.1_20251103`` for better performance.
+      {% endif %}
+
      .. note::

         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
@@ -122,7 +128,7 @@ Supported models
      {% endfor %}
   {% endfor %}

-.. _vllm-benchmark-performance-measurements-1024:
+.. _vllm-benchmark-performance-measurements-1210:

 Performance measurements
 ========================
@@ -178,7 +184,7 @@ Benchmarking
   Once the setup is complete, choose between two options to reproduce the
   benchmark results:

-   .. _vllm-benchmark-mad-1024:
+   .. _vllm-benchmark-mad-1210:

   {% for model_group in model_groups %}
      {% for model in model_group.models %}
@@ -190,7 +196,7 @@ Benchmarking
         .. tab-item:: MAD-integrated benchmarking

            The following run command is tailored to {{ model.model }}.
-            See :ref:`vllm-benchmark-supported-models-1024` to switch to another available model.
+            See :ref:`vllm-benchmark-supported-models-1210` to switch to another available model.

            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
               directory and install the required packages on the host machine.
@@ -219,7 +225,7 @@ Benchmarking
            and ``{{ model.mad_tag }}_serving.csv``.

            Although the :ref:`available models
-            <vllm-benchmark-available-models-1024>` are preconfigured to collect
+            <vllm-benchmark-available-models-1210>` are preconfigured to collect
            offline throughput and online serving performance data, you can
            also change the benchmarking parameters. See the standalone
            benchmarking tab for more information.
@@ -244,7 +250,7 @@ Benchmarking
         .. tab-item:: Standalone benchmarking

            The following commands are optimized for {{ model.model }}.
-            See :ref:`vllm-benchmark-supported-models-1024` to switch to another available model.
+            See :ref:`vllm-benchmark-supported-models-1210` to switch to another available model.

            .. seealso::

@@ -438,6 +444,14 @@ To reproduce this ROCm-enabled vLLM Docker image release, follow these steps:

      Replace ``vllm-rocm`` with your desired image tag.

+Known issues
+============
+
+There is a known regression with AITER for MoE models such as Mixtral and
+DeepSeek-R1. Consider using the :doc:`previous release
+<previous-versions/vllm-0.11.1-20251103>`
+(``rocm/vllm:rocm7.0.0_vllm_0.11.1_20251103``) for better performance.
+
 Further reading
 ===============

--- a/docs/how-to/rocm-for-ai/inference/index.rst
+++ b/docs/how-to/rocm-for-ai/inference/index.rst
@@ -26,7 +26,6 @@ training, fine-tuning, and inference. It leverages popular machine learning fram

 - :doc:`SGLang inference performance testing <benchmark-docker/sglang>`

- :doc:`Deploying your model <deploy-your-model>`
-
 - :doc:`xDiT diffusion inference <xdit-diffusion-inference>`

+- :doc:`Deploying your model <deploy-your-model>`
--- a/docs/how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst
+++ b/docs/how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst
@@ -11,11 +11,14 @@ xDiT diffusion inference

 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml

-   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
-   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+   {% set docker = data.docker %}
+
+   The `rocm/pytorch-xdit <{{ docker.docker_hub_url }}>`_ Docker image offers
+   a prebuilt, optimized environment based on `xDiT
+   <https://github.com/xdit-project/xDiT>`_ for benchmarking diffusion model
+   video and image generation on AMD Instinct MI355X, MI350X (gfx950), MI325X,
+   and MI300X (gfx942) GPUs.

-   The `rocm/pytorch-xdit <{{ docker.docker_hub_url }}>`_ Docker image offers a prebuilt, optimized environment based on `xDiT <https://github.com/xdit-project/xDiT>`_ for
-   benchmarking diffusion model video and image generation on gfx942 and gfx950 series (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X) GPUs.
   The image runs ROCm **{{docker.ROCm}}** (preview) based on `TheRock <https://github.com/ROCm/TheRock>`_
   and includes the following components:

@@ -27,9 +30,9 @@ xDiT diffusion inference
         * - Software component
           - Version

-         {% for component_name, component_version in docker.components.items() %}
-         * - {{ component_name }}
-           - {{ component_version }}
+         {% for component_name, component_data in docker.components.items() %}
+         * - `{{ component_name }} <{{ component_data.url }}>`_
+           - {{ component_data.version }}
         {% endfor %}

 Follow this guide to pull the required image, spin up a container, download the model, and run a benchmark.
@@ -37,10 +40,10 @@ For preview and development releases, see `amdsiloai/pytorch-xdit <https://hub.d

 What's new
 ==========
+
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml

-   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
-   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+   {% set docker = data.docker %}

   {% for item in docker.whats_new %}
   * {{ item }}
@@ -57,14 +60,7 @@ vary by model -- select one to get started.

 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml

-   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
-   {% set model_groups = data.xdit_diffusion_inference.model_groups %}
-   
-   {# Create a lookup for supported models #}
-   {% set supported_lookup = {} %}
-   {% for supported in docker.supported_models %}
-   {% set _ = supported_lookup.update({supported.group: supported.models}) %}
-   {% endfor %}
+   {% set docker = data.docker %}

   .. raw:: html

@@ -72,10 +68,8 @@ vary by model -- select one to get started.
          <div class="row gx-0">
              <div class="col-2 me-1 px-2 model-param-head">Model</div>
              <div class="row col-10 pe-0">
-        {% for model_group in model_groups %}
-            {% if model_group.group in supported_lookup %}
-                  <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
-            {% endif %}
+        {% for model_group in docker.supported_models %}
+               <div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.js_tag }}" tabindex="0">{{ model_group.group }}</div>
        {% endfor %}
              </div>
          </div>
@@ -83,29 +77,24 @@ vary by model -- select one to get started.
          <div class="row gx-0 pt-1">
              <div class="col-2 me-1 px-2 model-param-head">Variant</div>
              <div class="row col-10 pe-0">
-        {% for model_group in model_groups %}
-            {% if model_group.group in supported_lookup %}
-            {% set supported_models = supported_lookup[model_group.group] %}
+        {% for model_group in docker.supported_models %}
            {% set models = model_group.models %}
            {% for model in models %}
-                {% if model.model in supported_models %}
                {% if models|length % 3 == 0 %}
-                <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.page_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+                <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.js_tag }}" data-param-group="{{ model_group.js_tag }}" tabindex="0">{{ model.model }}</div>
                {% else %}
-                <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.page_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
-                {% endif %}
+                <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.js_tag }}" data-param-group="{{ model_group.js_tag }}" tabindex="0">{{ model.model }}</div>
                {% endif %}
            {% endfor %}
-            {% endif %}
        {% endfor %}
              </div>
          </div>
      </div>

-   {% for model_group in model_groups %}
+   {% for model_group in docker.supported_models %}
       {% for model in model_group.models %}

-   .. container:: model-doc {{ model.page_tag }}
+   .. container:: model-doc {{ model.js_tag }}

      .. note::

@@ -136,7 +125,7 @@ Pull the Docker image

 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml

-   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
+   {% set docker = data.docker %}

   For this tutorial, it's recommended to use the latest ``{{ docker.pull_tag }}`` Docker image.
   Pull the image using the following command:
@@ -148,15 +137,17 @@ Pull the Docker image
 Validate and benchmark
 ======================

-Once the image has been downloaded you can follow these steps to
-run benchmarks and generate outputs.
-
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml

-   {% for model_group in model_groups %}
+   {% set docker = data.docker %}
+
+   Once the image has been downloaded you can follow these steps to
+   run benchmarks and generate outputs.
+
+   {% for model_group in docker.supported_models %}
     {% for model in model_group.models %}

-   .. container:: model-doc {{model.page_tag}}
+   .. container:: model-doc {{model.js_tag}}

      The following commands are written for {{ model.model }}.
      See :ref:`xdit-video-diffusion-supported-models` to switch to another available model.
@@ -171,12 +162,11 @@ You can either use an existing Hugging Face cache or download the model fresh in

 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml

-   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
-   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+   {% set docker = data.docker %}

-   {% for model_group in model_groups %}
+   {% for model_group in docker.supported_models %}
     {% for model in model_group.models %}
-   .. container:: model-doc {{model.page_tag}}
+   .. container:: model-doc {{model.js_tag}}

      .. tab-set::

@@ -264,11 +254,12 @@ Run inference

 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml

-   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
-   {% for model_group in model_groups %}
+   {% set docker = data.docker %}
+
+   {% for model_group in docker.supported_models %}
     {% for model in model_group.models %}

-   .. container:: model-doc {{ model.page_tag }}
+   .. container:: model-doc {{ model.js_tag }}

      .. tab-set::

@@ -309,7 +300,7 @@ Run inference
               mkdir results

               torchrun --nproc_per_node=8 run.py \
-                  --model tencent/HunyuanVideo \
+                  --model {{ model.model_repo }} \
                  --prompt "In the large cage, two puppies were wagging their tails at each other." \
                  --height 720 --width 1280 --num_frames 129 \
                  --num_inference_steps 50 --warmup_steps 1 --n_repeats 1 \
@@ -317,40 +308,45 @@ Run inference
                  --enable_tiling --enable_slicing \
                  --use_torch_compile \
                  --bench_output results
+
            {% endif %}
            {% if model.model == "Wan2.1" %}
-               cd Wan2.1
+               cd Wan
               mkdir results

-               torchrun --nproc_per_node=8 run.py \
-                  --task i2v-14B \
-                  --size 720*1280 --frame_num 81 \
-                  --ckpt_dir "${HF_HOME}/hub/models--Wan-AI--Wan2.1-I2V-14B-720P/snapshots/8823af45fcc58a8aa999a54b04be9abc7d2aac98/" \
-                  --image "/app/Wan2.1/examples/i2v_input.JPG" \
-                  --ulysses_size 8 --ring_size 1 \
+               torchrun --nproc_per_node=8 /app/Wan/run.py \
+                  --task i2v \
+                  --height 720 \
+                  --width 1280 \
+                  --model {{ model.model_repo }} \
+                  --img_file_path /app/Wan/i2v_input.JPG \
+                  --ulysses_degree 8 \
+                  --seed 42 \
+                  --num_frames 81 \
                  --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside." \
-                  --benchmark_output_directory results --save_file video.mp4 --num_benchmark_steps 1 \
-                  --offload_model 0 \
-                  --vae_dtype bfloat16 \
-                  --allow_tf32 \
-                  --compile
+                  --num_repetitions 1 \
+                  --num_inference_steps 40 \
+                  --use_torch_compile
+
            {% endif %}
            {% if model.model == "Wan2.2" %}
-               cd Wan2.2
+               cd Wan
               mkdir results

-               torchrun --nproc_per_node=8 run.py \
-                  --task i2v-A14B \
-                  --size 720*1280 --frame_num 81 \
-                  --ckpt_dir "${HF_HOME}/hub/models--Wan-AI--Wan2.2-I2V-A14B/snapshots/206a9ee1b7bfaaf8f7e4d81335650533490646a3/" \
-                  --image "/app/Wan2.2/examples/i2v_input.JPG" \
-                  --ulysses_size 8 --ring_size 1 \
+               torchrun --nproc_per_node=8 /app/Wan/run.py \
+                  --task i2v \
+                  --height 720 \
+                  --width 1280 \
+                  --model {{ model.model_repo }} \
+                  --img_file_path /app/Wan/i2v_input.JPG \
+                  --ulysses_degree 8 \
+                  --seed 42 \
+                  --num_frames 81 \
                  --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside." \
-                  --benchmark_output_directory results --save_file video.mp4 --num_benchmark_steps 1 \
-                  --offload_model 0 \
-                  --vae_dtype bfloat16 \
-                  --allow_tf32 \
-                  --compile
+                  --num_repetitions 1 \
+                  --num_inference_steps 40 \
+                  --use_torch_compile
+
            {% endif %}

            {% if model.model == "FLUX.1" %}
@@ -358,7 +354,7 @@ Run inference
               mkdir results

               torchrun --nproc_per_node=8 /app/Flux/run.py \
-                  --model black-forest-labs/FLUX.1-dev \
+                  --model {{ model.model_repo }} \
                  --seed 42 \
                  --prompt "A small cat" \
                  --height 1024 \
@@ -369,12 +365,28 @@ Run inference
                  --no_use_resolution_binning \
                  --ulysses_degree 8 \
                  --use_torch_compile \
-                  --num_repetitions 1 \
-                  --benchmark_output_directory results
+                  --num_repetitions 50

            {% endif %}

-            The generated video will be stored under the results directory. For the actual benchmark step runtimes, see {% if model.model == "Hunyuan Video" %}stdout.{% elif model.model in ["Wan2.1", "Wan2.2"] %}results/outputs/rank0_*.json{% elif model.model == "FLUX.1" %}results/timing.json{% endif %}
+            {% if model.model == "stable-diffusion-3.5-large" %}
+               cd StableDiffusion3.5 
+               mkdir results
+
+               torchrun --nproc_per_node=8 /app/StableDiffusion3.5/run.py \
+                  --model {{ model.model_repo }} \
+                  --num_inference_steps 28 \
+                  --prompt "A capybara holding a sign that reads Hello World" \
+                  --use_torch_compile \
+                  --pipefusion_parallel_degree 4 \
+                  --use_cfg_parallel \
+                  --num_repetitions 50 \
+                  --dtype torch.float16 \
+                  --output_path results
+
+            {% endif %}
+
+            The generated video will be stored under the results directory. For the actual benchmark step runtimes, see {% if model.model == "Hunyuan Video" %}stdout.{% elif model.model in ["Wan2.1", "Wan2.2"] %}results/outputs/rank0_*.json{% elif model.model == "FLUX.1" %}results/timing.json{% elif model.model == "stable-diffusion-3.5-large"%}benchmark_results.csv{% endif %}

            {% if model.model == "FLUX.1" %}You may also use ``run_usp.py`` which implements USP without modifying the default diffusers pipeline. {% endif %}

@@ -385,4 +397,4 @@ Previous versions
 =================

 See :doc:`benchmark-docker/previous-versions/xdit-history` to find documentation for previous releases
-of xDiT diffusion inference performance testing.
+of xDiT diffusion inference performance testing.