Comparing
quora:kryang/fix-streaming-tool-args-upstream
(6164735
) withlitellm_oss_staging_04_13_2026_p1
(f2f2a91
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py+1%
418.7 µs414.8 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+1%
85.1 µs84.6 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.6 µs187.3 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.4 µs85.3 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.2 µs85.2 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
543.4 µs544.2 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.5 µs87.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239 µs239.4 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
543 µs544.2 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
88 µs88.5 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-1%
570 µs573.5 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py-1%
143.2 µs144.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
146.6 µs147.6 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-1%
149.2 µs151.3 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-2%
142 µs144.4 µs
Commits
Click on a commit to change the comparison rangeBase
main
f2f2a91
-0.39%
test: add tests for input_json_delta emission on bundled tool args
f797b16
7 days ago
by krisyang1125-0.14%
style: apply Black formatting to streaming_iterator.py
ad2c039
7 days ago
by krisyang1125+0.23%
test: make no_extra_delta tests assert explicitly instead of passing silently
6164735
7 days ago
by krisyang1125