[TRTLLM-14388][refactor] BREAKING: Remove 2-model code and tests

[mikeiovine]

Description

Remove 2-model code and related tests. We are past the deprecation period and all feature gaps have been closed.

Some 2-model code is left behind for a few niche things that can't use 1-model (ngram, user-provided).

Test Coverage

Existing tests.

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

Dev Engineer Review

• Removes deprecated two-model speculative decoding paths, including draft-engine orchestration, ModelDrafter, MTPDraftModelForCausalLM, Eagle3SpecMetadata, and related CUDA-graph and KV-cache branches.
• Consolidates Eagle3 and MTP Eagle routing around one-model execution while retaining NGram and user-provided speculative decoding paths.
• Removes breaking API fields, enum members, constructor parameters, and helper arguments such as eagle3_one_model, mtp_eagle_one_model, is_draft_model, and draft_model_engine.
• Updates speculative-decoding validation, sampler selection, resource-manager creation, metadata handling, attention metadata APIs, and model constructors for consistent mode dispatch.
• Updates examples, documentation, manifests, configuration files, test baselines, QA lists, and waiver entries to remove deprecated options.
• Verify all callers use the revised public signatures and that remaining two-model support is limited to documented niche modes.
• Verify CI failures reported in the L0 merge-request pipeline before approval. Confirm that the updated test-list entries match valid parametrized test identifiers and contain no duplicates.

QA Engineer Review

• Modified integration tests include Eagle3 and MTP accuracy tests, disaggregated serving tests, AutoDeploy tests, speculative-decoding examples, performance sanity tests, and end-to-end quickstart tests.
• Removed speculative-decoding tests include test_draft_token_prepare_for_generation and test_draft_token_tree_sampling.
• Renamed or simplified tests include test_eagle3, test_eagle3_spec_decoding_stats, test_multi_eagle3, test_get_num_spec_layers_*, test_accepts_mtp_eagle, test_detect_hidden_states_capture_last_layer_for_mtp_eagle, and test_autodeploy_eagle3_acceptance_rate.
• Updated test implementations are represented in tests/integration/test_lists/test-db/, tests/integration/test_lists/qa/, and tests/integration/test_lists/waives.txt where applicable.
• Removed two-model MTP coverage from l0_b200.yml.
• Verdict: needs follow-up until the reported L0 pipeline failures are investigated and CBTS coverage is confirmed.

[mikeiovine]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #59235 [ run ] triggered by Bot. Commit: 95afa29 Link to invocation

[tensorrt-cicd]

PR_Github #59235 [ run ] completed with state ABORTED. Commit: 95afa29

Link to invocation

[mikeiovine]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #59758 [ run ] triggered by Bot. Commit: 97e26c8 Link to invocation

[mikeiovine]

/bot run --disable-fail-fast

[mikeiovine]

/bot run

[mikeiovine]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #63808 [ run ] triggered by Bot. Commit: 841a59e Link to invocation

[tensorrt-cicd]

PR_Github #63809 [ run ] triggered by Bot. Commit: 841a59e Link to invocation

[tensorrt-cicd]

PR_Github #63808 [ run ] completed with state ABORTED. Commit: 841a59e

Link to invocation

[tensorrt-cicd]

PR_Github #63809 [ run ] completed with state FAILURE. Commit: 841a59e
/LLM/main/L0_MergeRequest_PR pipeline #51753 completed with status: 'FAILURE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[mikeiovine]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #64076 [ run ] triggered by Bot. Commit: 46245ad Link to invocation

[mikeiovine]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #64089 [ run ] triggered by Bot. Commit: c4aa7ba Link to invocation

[tensorrt-cicd]

PR_Github #64076 [ run ] completed with state ABORTED. Commit: 46245ad

Link to invocation

[tensorrt-cicd]

PR_Github #64089 [ run ] completed with state SUCCESS. Commit: c4aa7ba
/LLM/main/L0_MergeRequest_PR pipeline #52016 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[mikeiovine]

/bot run --disable-fail-fast

[mikeiovine]

/bot cancel

[github-actions]

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

Details

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental) --high-priority]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Supports wildcard * for pattern matching (e.g., "*PerfSanity*" matches all stages containing PerfSanity). Examples: "A10-PyTorch-1, xxx", "PerfSanity". The patterns "*", "*Post-Merge*", and "*PerfSanity*", including equivalent escaped or repeated-star forms and their use in comma-separated lists, require the ci: post-merge approved PR label. Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Requires the ci: full pre-merge approved label on the PR (ask a member of NVIDIA/trt-llm-ci-approvers). Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline. Requires the ci: full pre-merge approved label on the PR (ask a member of NVIDIA/trt-llm-ci-approvers).

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline. Requires the ci: post-merge approved PR label applied by an active member of NVIDIA/trt-llm-ci-approvers. The approval label remains in place when new commits are pushed.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Supports wildcard * for pattern matching. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx", --extra-stage "Post-Merge". The patterns "*", "*Post-Merge*", and "*PerfSanity*", including equivalent escaped or repeated-star forms and their use in comma-separated lists, require the ci: post-merge approved PR label.

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

--high-priority (OPTIONAL) : Run the pipeline with high priority. This option is restricted to authorized users only and will route the job to a high-priority queue.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

[mikeiovine]

I am going to split up this PR. There are more merge conflicts than I anticipated

[tensorrt-cicd]

PR_Github #64362 [ ] completed with state FAILURE. Commit: de87af2
Not allowed on merged PR

Link to invocation