pike00:fix-prisma-engine-leak-26619 - Branch - BerriAI/litellm

fix(proxy): prevent Prisma engine orphan leak on shutdown disconnect failure (#26619)

#28755

Merging

pike00:fix-prisma-engine-leak-26619

into

litellm_oss_branch

N/A

New: 16

Benchmarks

16 total

test_cost_per_token_anthropic

tests/benchmarks/test_benchmarks.py

N/A

N/A558.9 µs

test_cost_per_token_openai

tests/benchmarks/test_benchmarks.py

N/A

N/A558.3 µs

test_get_llm_provider_anthropic

tests/benchmarks/test_benchmarks.py

N/A

N/A142.4 µs

test_get_llm_provider_azure

tests/benchmarks/test_benchmarks.py

N/A

N/A144.5 µs

test_get_llm_provider_openai

tests/benchmarks/test_benchmarks.py

N/A

N/A138.8 µs

test_token_counter_long_content

tests/benchmarks/test_benchmarks.py

N/A

N/A1.7 ms

test_get_llm_provider_with_prefix

tests/benchmarks/test_benchmarks.py

N/A

N/A137.4 µs

test_token_counter_multi_turn

tests/benchmarks/test_benchmarks.py

N/A

N/A565.6 µs

test_get_model_cost_key_case_insensitive

tests/benchmarks/test_benchmarks.py

N/A

N/A82.4 µs

test_token_counter_raw_text

tests/benchmarks/test_benchmarks.py

N/A

N/A184.3 µs

test_get_model_cost_key_exact_match

tests/benchmarks/test_benchmarks.py

N/A

N/A80 µs

test_token_counter_simple_message

tests/benchmarks/test_benchmarks.py

N/A

N/A235.6 µs

test_get_model_info_anthropic

tests/benchmarks/test_benchmarks.py

N/A

N/A79.2 µs

test_token_counter_with_tools

tests/benchmarks/test_benchmarks.py

N/A

N/A412.2 µs

test_get_model_info_openai

tests/benchmarks/test_benchmarks.py

N/A

N/A82.7 µs

test_get_model_info_with_provider

tests/benchmarks/test_benchmarks.py

N/A

N/A80.3 µs

Commits

Click on a commit to change the comparison range

No baseline data is yet availableOnce your main branch has generated a first performance report, you will see the list of commits and their performance impact here.

Home Terms Privacy Docs