chore(versions): align tutorials examples with 26.08 release train (#167)

[mc-nv]

What does the PR do?

• Aligns the tutorial examples with the 26.08 release train.
• main follows the train too, so this lands here as well as on r26.08 (precedent: 69217d9 for 26.06, d478e30 for 26.07).

Checklist

• PR title reflects the change and is of format <commit_type>: <Title>
• Changes are described in the pull request.
• Related issues are referenced.
• Populated github labels field
• Added test plan and verified test passes.
• Verified that the PR passes existing CI.
• Verified copyright is correct on all changed files.
• Added succinct git squash message before merging ref.
• All template sections are filled out.
• Optional: Additional screenshots for behavior/output changes with before/after.

Commit Type:

Check the conventional commit type
box here and add the label to the github PR.

• build
• ci
• docs
• feat
• fix
• perf
• refactor
• revert
• style
• test

Related PRs:

• build(deps): Bump Go example gRPC client dependencies (#919) client#920
• build(before-code-freeze): Align CMake configuration with the other repos (#162) common#164
• fix: reserve completion-queue slot at enqueue to restore preserve_ordering (#520) core#523
• build(before-code-freeze): Prepare the ONNX Runtime backend for the manylinux base (#352) onnxruntime_backend#358
• build(before-code-freeze): Export the stub's dynamic symbols when libpython is static (#451) python_backend#453
• build: Fix manylinux Python version (#204) pytorch_backend#209
• chore(post-release): advance main to 26.08 upstreams server#8949

Where should the reviewer start?

Quick_Deploy/HuggingFaceTransformers/Dockerfile — representative of the container-tag bumps across the 19 files.

Test plan:

• Full CI run on the internal pipeline at TRITON_CONTAINER_VERSION=26.09dev_user, with TRITON_NIGHTLY=1 and TRITON_SBSA=1.

• Local verification: per-repo pre-commit run --files <changed> passes with no auto-fixes.

• CI Pipeline ID:

Caveats:

• Do not merge before the model-repository mount point is rotated: TRITON_SERVER_MODEL_REPO_VERSION derives from TRITON_CONTAINER_VERSION, so 26.09dev must exist on the share first.

Background

Post-release step of the 26.08 train: the default branches move onto the same upstream containers as the just-released r26.08, and pick up the fixes that landed only on the release branch while it stabilised.

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

• Relates to: TRI-1691

[greptile-apps]

Greptile Summary

This PR aligns runnable tutorial examples with the Triton 26.08 release train.

• Updates Triton server, SDK, vLLM, and TensorRT-LLM container references across conceptual, model, deployment, and quick-start guides.
• Updates Python API build defaults and generated image tags to 26.08.
• Keeps related Kubernetes benchmark and model-preparation pods on the same release version.

Confidence Score: 5/5

The PR appears safe to merge because the changed references and build tags consistently advance the affected tutorials to Triton 26.08.

The diff is limited to coordinated release-tag updates, and investigation found no changed-code-triggered build, runtime, data, or security failure.

Important Files Changed

Filename	Overview
Quick_Deploy/HuggingFaceTransformers/Dockerfile	Updates the tutorial base image from Triton 26.07 to 26.08 with no other build changes.
Triton_Inference_Server_Python_API/build.sh	Consistently updates primary and diffusion output tags to 26.08 within the changed build path.
Triton_Inference_Server_Python_API/docker/Dockerfile	Updates the default Triton base image tag to 26.08.
Deployment/Kubernetes/EKS_Multinode_Triton_TRTLLM/multinode_helm_chart/containers/triton_trt_llm.containerfile	Moves the EKS distributed-serving custom image onto the 26.08 TensorRT-LLM base.
Deployment/Kubernetes/EKS_Multinode_Triton_TRTLLM/multinode_helm_chart/gen_ai_perf.yaml	Updates the benchmark pod to the matching 26.08 SDK image.
Feature_Guide/Speculative_Decoding/vLLM/README.md	Updates the executable vLLM speculative-decoding command to use the 26.08 backend image.
Popular_Models_Guide/StableDiffusion/README.md	Updates the documented Triton release reference to 26.08; no new actionable defect was established.

_{Reviews (1): Last reviewed commit: "chore(versions): align tutorials example..." | Re-trigger Greptile}