fix(agentx): route synthesized warmup concurrency ramp / 修复自动生成预热阶段的并发爬升 - #38
Open
ivanium wants to merge 1 commit into
Open
fix(agentx): route synthesized warmup concurrency ramp / 修复自动生成预热阶段的并发爬升#38ivanium wants to merge 1 commit into
ivanium wants to merge 1 commit into
Conversation
Preserve --warmup-concurrency-ramp-duration on the AgentX profiling source phase and apply it only to the synthesized warmup. Add focused converter and timing tests plus generated schema and documentation updates.\n\n中文：将 --warmup-concurrency-ramp-duration 从 AgentX 的分析源阶段传递到自动生成的预热阶段，并确保该配置不会影响正式分析阶段。补充转换、时序测试及对应的配置 Schema 和文档更新。 Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Try out this PRQuick install: pip install --upgrade --force-reinstall git+https://github.com/ai-dynamo/aiperf.git@5685fc795b6f2de094c47e8962409ddecfc654b6Recommended with virtual environment (using uv): uv venv --python 3.12 && source .venv/bin/activate
uv pip install --upgrade --force-reinstall git+https://github.com/ai-dynamo/aiperf.git@5685fc795b6f2de094c47e8962409ddecfc654b6Last updated for commit: |
ivanium
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
--warmup-concurrency-ramp-durationon the profiling phase that sources AgentX auto-warmupNeeded by SemiAnalysisAI/InferenceX#2302, where 815 mandatory snapshot primers overloaded a narrow Dynamo prefill ingress because the accepted ramp flag was silently dropped.
Validation
uv run pytest -q tests/unit/config/test_converter_profiling_phase_routes.py tests/unit/timing/test_phase_config_agentic_replay.py tests/unit/config/test_config_schema_generator_integration.py(96 passed)uv run pre-commit run中文说明
--warmup-concurrency-ramp-duration保留在用于生成 AgentX 自动预热的分析阶段配置中该修复用于 SemiAnalysisAI/InferenceX#2302。此前 815 个强制快照预热请求会压垮较窄的 Dynamo 预填充入口，因为命令行虽然接受了并发爬升参数，但在自动生成预热阶段时将其静默丢弃。