Comparing
Chesars:fix/azure-streaming-role-include-usage
(ce16db1
) withlitellm_staging_03_22_2026
(c89496f
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+2%
86.9 µs85.3 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py+1%
189.2 µs186.8 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.4 µs84.9 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143.4 µs142.7 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
544.6 µs542.4 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
88.2 µs87.9 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.7 µs87.4 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.3 µs145.9 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
142 µs141.8 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
542.9 µs543.1 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.8 µs149 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.5 µs240.2 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
415.9 µs418 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
84.1 µs84.8 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-1%
567.6 µs574.8 µs
Commits
Click on a commit to change the comparison rangeBase
main
c89496f
+0.14%
fix: preserve role='assistant' in Azure streaming with include_usage
ce16db1
2 months ago
by Chesars