[ci] add legacy test workflow and test config

[zhulinJulia24]

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[Copilot]

Pull request overview

Adds “legacy” CI workflows and corresponding autotest configuration to support running older E2E / evaluation / benchmark pipelines, while updating autotest model matrices and some runtime behaviors (e.g., RESTful chat streaming and cache tuning) to align with current model coverage.

Changes:

• Add new legacy GitHub Actions workflows for daily E2E, API eval, MLLM API eval, and benchmarks.
• Add legacy autotest YAML configs and update existing configs/model lists used by CI and autotest.
• Update RESTful chat autotest to use streaming outputs; adjust some PR-test model selections and pipeline test matrices.

Reviewed changes

Copilot reviewed 18 out of 18 changed files in this pull request and generated 10 comments.

Show a summary per file

File	Description
autotest/utils/run_restful_chat.py	Switch RESTful chat test to stream responses and add case filtering for code models.
autotest/utils/config_utils.py	Add model/env-specific cache-max-entry-count tuning in generated run configs.
autotest/tools/quantization/test_quantization_awq.py	Update PR AWQ quantization model and how the PR test selects GPUs.
autotest/tools/pipeline/test_pipeline_chat_turbomind_mllm.py	Add PR-test coverage for turbomind MLLM pipeline on 2 GPUs.
autotest/tools/common_case_config.py	Refresh PR/fallback model sets for LLM/MLLM, toolcall, and reasoning configs.
autotest/config_legacy.yml	New legacy autotest configuration (paths, model lists, quantization lists).
autotest/config_h_legacy.yml	New “h” legacy autotest configuration (minimal model/quant lists).
autotest/config_h.yml	Update “h” environment model lists and TP mappings (remove some Intern-S1 entries, add VL/InternVL3_5 entries).
autotest/config.yml	Update primary autotest model lists, quantization lists, and benchmark/eval selections.
autotest/benchmark/test_throughput_performance.py	Update benchmark model from Qwen3-VL-32B to Qwen3-VL-30B-A3B.
autotest/benchmark/test_prefixcache_performance.py	Update benchmark model from Qwen3-VL-32B to Qwen3-VL-30B-A3B.
autotest/benchmark/test_apiserver_performance.py	Update benchmark model from Qwen3-VL-32B to Qwen3-VL-30B-A3B.
.github/workflows/mllm_api_eval_legacy.yml	Add legacy MLLM API evaluation workflow.
.github/workflows/evaluate.yml	Pin transformers in the evaluation workflow environment step.
.github/workflows/daily_ete_test_legacy.yml	Add legacy daily end-to-end test workflow.
.github/workflows/daily_ete_test.yml	Change scheduled behavior for RESTful job and adjust RESTful test model matrix.
.github/workflows/benchmark_legacy.yml	Add legacy benchmark workflow.
.github/workflows/api_eval_legacy.yml	Add legacy API evaluation workflow.

Comments suppressed due to low confidence (1)

autotest/tools/common_case_config.py:126

• This gpu_num_2 fallback config sets parallel_config.tp to 1, so the test marked for 2 GPUs may actually run single-GPU. If the intention is a TP2 fallback run, set tp: 2 here to match the marker and the test function name (*_tp2).

    'communicator': 'nccl',
    'quant_policy': 8,
    'parallel_config': {
        'tp': 1
    },

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 19 out of 19 changed files in this pull request and generated 4 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 24 out of 24 changed files in this pull request and generated 5 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.