Comparing
cwang-otto:fix/aresponses-streaming-fallback-upstream
(9bc5e21
) withmain
(a72414a
)-1%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-4%
80.3 µs83.6 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-4%
78.5 µs81.7 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-2%
136.5 µs139 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-2%
143.6 µs146 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py-2%
137.9 µs140 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+2%
1.7 ms1.7 ms
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
142.1 µs144.2 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+1%
80.4 µs79.9 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
556.2 µs559.8 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py-1%
554.6 µs557.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
182.8 µs182.1 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
234.9 µs235.6 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
81.7 µs81.9 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.4 µs79.6 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
411.3 µs411.9 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
562.5 µs562.5 µs
Commits
Click on a commit to change the comparison rangeBase
main
a72414a
-0.87%
fix(router): wrap aresponses streaming iterator for mid-stream fallbacks
9bc5e21
3 months ago
by cwang-otto