[Graph Optimization][BugFix][CI] Fix 0size bug && add unitest

[DrRyanHuang]

Motivation

#5078 导致所有 SOT+CUDAGraph 模型启动失败:

FastDeploy/fastdeploy/model_executor/layers/embeddings.py

Lines 302 to 303 in 3bdd54e

	if ids_remove_padding.shape[0] == 0:
	return paddle.empty([0, self.embedding_dim], dtype=self.embeddings.weight.dtype)

上面的 .shape[0] == 0 会引入一个 memcpy_h2d 操作，导致 CUDAGraph 无法启动

目前可通过 forward_meta.is_zero_size 规避

if forward_meta is not None and forward_meta.is_zero_size:
    return paddle.empty([0, self.embedding_dim], dtype=self.embeddings.weight.dtype)

Caution

当前PR只是一个临时解决方案，当输入真的是 0 size 的时候，SOT会重新组网，虽然不会打断，但会存在两张整图
由于我们之前做过约束，仅允许存在一张图，FastDeploy 会直接报错退出
由于目前非 EP 场景不存在 0 size输入，而SOT也没有开始适配EP场景，所以目前无需担心
后续需要分布式算子支持0size输入，之后再移除 ForwardMeta 中的 is_zero_size

Modifications

• 添加单测 test_EB_Lite_sot_serving 添加到 base 的 yaml 中了
• 修改单测 test_EB_VL_Lite_sot_serving 启动参数，graph_opt_level = 2 SOT => CINN
• 给 ForwardMeta 添加 is_zero_size

Usage or Command

python -m fastdeploy.entrypoints.openai.api_server \
       --model $MODEL \
       --port $PORT \
       --metrics-port $MPPPPP \
       --engine-worker-queue-port $EWQPPP \
       --tensor-parallel-size 1 \
       --max-model-len 32768 \
       --max-num-seqs 128 \
       --graph-optimization-config '{"graph_opt_level":2, "use_cudagraph":true}' \
       --quantization wint4 \
       --enable-mm \
       --max-num-batched-tokens 172 \
       --enable-chunked-prefill \
       --kv-cache-ratio 0.71 \
       --quantization wint4 \
       --reasoning-parser ernie-45-vl 

Accuracy Tests

NO NEED

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 80.00000% with 1 line in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@9f4512c). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/model_executor/layers/embeddings.py	50.00%	0 Missing and 1 partial ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5495   +/-   ##
==========================================
  Coverage           ?   60.27%           
==========================================
  Files              ?      329           
  Lines              ?    41116           
  Branches           ?     6261           
==========================================
  Hits               ?    24784           
  Misses             ?    14443           
  Partials           ?     1889           

Flag	Coverage Δ
GPU	60.27% <80.00%> (?)

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.

[gongshaotian]

LGTM