[None] [feat] Add Tencent HunYuanMoEV1 model support

[qianbiaoxiang]

Description

Currently, the Hunyuan inference team supports the Hunyuan-A13B model. By adding the modeling_hunyuan_moe.py related files, it supports the model of HunYuanMoEV1ForCausalLM.

We have validated the accuracy of this PR，HunYuan (new MoE LLM model from Tencent) will open source these days.

Thanks~

Test Coverage

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.

run [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]

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

--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 "A10-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-1, xxx". 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.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. 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. Will also run L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-[Post-Merge]-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md.

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.

Summary by CodeRabbit

• New Features

  • Advanced LLM quickstart: new CLI flag to optionally apply chat-template formatting to prompts.
  • New HunYuan MoE causal LM model exposed for Torch users.
  • Tokenizer: ability to retrieve chat templates.
  • RoPE: dynamic scaling mode with configurable alpha and added QK-normalization support for attention.

• Bug Fixes

  • Safer MLA detection before enabling flash MLA.
  • Clearer tokenizer loading warnings with exception details.

[wm2012011492]

/bot run

[tensorrt-cicd]

PR_Github #10260 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10260 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #7581 completed with status: 'FAILURE'

[byshiue]

/bot run

[tensorrt-cicd]

PR_Github #15060 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #15060 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #11371 completed with status: 'FAILURE'

[byshiue]

/bot run

[tensorrt-cicd]

PR_Github #15089 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #15089 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #11392 completed with status: 'FAILURE'

[byshiue]

/bot run

[tensorrt-cicd]

PR_Github #15102 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #15102 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #11402 completed with status: 'FAILURE'

[byshiue]

/bot run

[tensorrt-cicd]

PR_Github #15193 [ run ] triggered by Bot

[byshiue]

/bot run

[tensorrt-cicd]

PR_Github #15298 [ run ] triggered by Bot

[QiJune]

LGTM

[tensorrt-cicd]

PR_Github #15298 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #11550 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

[byshiue]

There are too many conservation due to wrong commit at the beginning. So, I bypass the merge after checking the comments we give, and ignore the comments of robot.