Comparing
lasso-security:rnd-5748-lasso-tool-calling
(c26bbb2
) withlitellm_internal_staging
(e58a561
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+1%
80.3 µs79.2 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-1%
136.8 µs138.5 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py+1%
237 µs235.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
184.3 µs183.4 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.9 µs80.2 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
143 µs142.4 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
544.3 µs542.2 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
563.6 µs565.7 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
80.2 µs80.5 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144.1 µs144.4 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.2 µs82.4 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
80 µs80.1 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.4 µs138.6 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
544.1 µs544.6 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
414 µs413.9 µs
Commits
Click on a commit to change the comparison rangeBase
main
e58a561
-0.13%
chore(lasso): black formatting + comment on expand skip branch (RND-5748)
87d92ca
4 months ago
by vladpolevoi+0.07%
fix(lasso): satisfy mypy in _handle_masking, _update_tool_calls_from_masked, _apply_masking_to_model_response (RND-5748)
c26bbb2
4 months ago
by vladpolevoi