Comparing
michelligabriele:fix/vertex-wif-pluggable-credential-dispatch
(1704bd0
) withlitellm_oss_staging_04_02_2026_p1
(d949085
)+1%
- Untouched
- 16
Benchmarks
16 total
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py+2%
143.7 µs141.5 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py+1%
150.4 µs148.5 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py+1%
144.9 µs143.2 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py+1%
148.8 µs147.2 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py+1%
545.4 µs540.1 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+1%
85.2 µs84.5 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py+1%
545.6 µs541.2 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py+1%
85.4 µs84.8 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
569.8 µs567 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.5 µs85.3 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.6 µs87.4 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239 µs238.4 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
87.4 µs87.4 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
417 µs417.5 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
186.6 µs186.9 µs
Commits
Click on a commit to change the comparison rangeBase
main
d949085
+0.58%
fix(vertex_ai): support pluggable (executable) credential_source for WIF auth
1704bd0
29 days ago
by michelligabriele