langchain-ai
langchain
BlogDocsChangelog

GitHub Actions run

3 hours ago e85d221 ambershen:optimize/llm-sync-generate-parallelization pull_request

Compare

Base
Search a run
Head
feat: parallelize sync generate method for improved LLM throughput
#34043
ambershen:optimize/llm-sync-generate-parallelization
3 hours ago
Wall TimeCPU Simulation
Compare
Suggested base runs:

Skipped (21)

Benchmarks

test_import_time[tool]
libs/core/tests/benchmarks/test_imports.py
497.3 ms
test_import_time[InMemoryVectorStore]
libs/core/tests/benchmarks/test_imports.py
589.4 ms
test_import_time[RunnableLambda]
libs/core/tests/benchmarks/test_imports.py
471.9 ms
test_import_time[LangChainTracer]
libs/core/tests/benchmarks/test_imports.py
421.3 ms
test_import_time[HumanMessage]
libs/core/tests/benchmarks/test_imports.py
260.4 ms
test_import_time[InMemoryRateLimiter]
libs/core/tests/benchmarks/test_imports.py
170.4 ms
test_async_callbacks_in_sync
libs/core/tests/benchmarks/test_async_callbacks.py
24.3 ms
test_import_time[CallbackManager]
libs/core/tests/benchmarks/test_imports.py
442.9 ms
test_import_time[PydanticOutputParser]
libs/core/tests/benchmarks/test_imports.py
512.2 ms
test_import_time[ChatPromptTemplate]
libs/core/tests/benchmarks/test_imports.py
570 ms
test_import_time[Runnable]
libs/core/tests/benchmarks/test_imports.py
472.7 ms
test_import_time[Document]
libs/core/tests/benchmarks/test_imports.py
183.6 ms
test_import_time[BaseChatModel]
libs/core/tests/benchmarks/test_imports.py
500.9 ms
© 2025 CodSpeed Technology
Home Terms Privacy Docs