[Feature] support glm tp+dp+ep

[ckl117]

Motivation

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

Modifications

Usage or Command

export FD_USE_DEEP_GEMM=1
quantization='{"quantization":"mix_quant","moe_quant_type":"block_wise_fp8"}'
# GLM4.5Air 仅MoE量化block_wise_fp8 AttnTP4+MoE EP8
python -m fastdeploy.entrypoints.openai.multi_api_server \
       --ports "8111,8122" \
       --num-servers 2 \
       --metrics-ports "8212,3212" \
       --args --model "/model/GLM-4.5-Air" \
       --engine-worker-queue-port "8377,8378" \
       --cache-queue-port "8477,8478" \
       --max-model-len 32768 \
       --max-num-seqs 128 \
       --tensor-parallel-size 4 \
       --data-parallel-size 2 \
       --enable-expert-parallel \
       --gpu-memory-utilization 0.8 \
       --quantization ${quantization} \
       --disable-custom-all-reduce

Accuracy Tests

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[paddle-bot]

Thanks for your contribution!

[codecov-commenter]

Codecov Report

❌ Patch coverage is 0% with 6 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@5c9bc13). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/model_executor/models/glm4_moe.py	0.00%	6 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #6317   +/-   ##
==========================================
  Coverage           ?   68.43%           
==========================================
  Files              ?      390           
  Lines              ?    52107           
  Branches           ?     8118           
==========================================
  Hits               ?    35660           
  Misses             ?    13845           
  Partials           ?     2602           

Flag	Coverage Δ
GPU	68.43% <0.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[yuanlehome]

再看看