Comparing
litellm_bedrock-normalize-custom-tool-schema
(ec91021
) withmain
(97f722f
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+1%
88.7 µs87.8 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py+1%
147.3 µs146.6 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
84.7 µs84.6 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.2 µs187.4 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143.1 µs143.2 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
567.3 µs568 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.3 µs239.7 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.9 µs149.2 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
86.5 µs86.7 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.2 µs85.5 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.3 µs87.7 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py-1%
543 µs545.8 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
541.3 µs544.3 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-1%
141.7 µs143 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py-1%
414.4 µs418.4 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
Commits
Click on a commit to change the comparison rangeBase
main
97f722f
+0.2%
feat(bedrock): normalize custom tool JSON schema for Invoke and Converse
8f4676a
8 days ago
by Sameerlite-0.47%
fix(bedrock): use iterative walk for custom→object schema normalization
83140e7
8 days ago
by Sameerlite+0.02%
fix(bedrock): custom tool schemas and missing tool names for Converse
ec91021
8 days ago
by Sameerlite