[AMD] Update v4 amd cookbook

[1am9trash]

Motivation

In the current SGLang Cookbook, the DeepSeek-V4 model only documents Docker / server commands for NVIDIA GPUs. This PR adds the AMD GPU (MI300X, MI355X) variants.

Modifications

• Add AMD verified cells to deepseek-v4.jsx: MI300X (Flash FP8) and MI355X (Flash / Pro, FP4 / FP8), single-node, TP-only at low concurrency and TP+DP at high concurrency, with EAGLE MTP.
• Map AMD checkpoints in modelNames (FP4: deepseek-ai/..., FP8: sgl-project/...-FP8) and add the lmsysorg/sglang-rocm ROCm images to dockerImages.
• Make the _deployment.jsx Docker wrapper vendor-aware: AMD emits --device=/dev/kfd/--device=/dev/dri/--group-add video instead of --gpus all.
• Update DeepSeek-V4.mdx: add an AMD ROCm Docker install section and an AMD configuration note.

Verification

Built the docs locally with mint dev and confirmed the DeepSeek-V4 page renders correctly (Deploy matrix, AMD cells, and Docker command generation all preview without issues).

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review and Merge Process

1. Ping Merge Oncalls to start the process. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments or contact authorized users to do so.
   • Common commands include /tag-and-rerun-ci, /tag-run-ci-label, /rerun-failed-ci
4. After green CI and required approvals, ask Merge Oncalls or people with Write permission to merge the PR.

---

CI States

Latest PR Test (Base): ✅ Run #27608625543
Latest PR Test (Extra): ❌ Run #27608625058

[gemini-code-assist]

Code Review

This pull request adds comprehensive support and documentation for running DeepSeek-V4 on AMD ROCm GPUs (specifically MI300X and MI355X). It introduces AMD-specific Docker run configurations, updates the deployment snippet to dynamically generate the correct Docker flags based on the GPU vendor, and adds benchmark mappings and detailed deployment configurations (including environment variables and CLI flags) for various quantization strategies (FP4 and FP8) on AMD hardware. I have no feedback to provide.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.