Comparing
awais786:fix/fireworks-base64-image-padding
(27894d4
) withlitellm_oss_staging_03_17_2026
(58e74a6
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+3%
88.1 µs85.3 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+3%
86 µs83.6 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+2%
89.4 µs87.4 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143.4 µs143 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
572.5 µs571.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
188.1 µs187.9 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
419.2 µs419 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.7 µs146.6 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
149.3 µs149.3 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.5 µs87.6 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.2 µs85.3 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.9 µs142.2 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
544.7 µs547.7 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py-1%
542.5 µs546 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py-1%
239.6 µs241.3 µs
Commits
Click on a commit to change the comparison rangeBase
main
58e74a6
+0.7%
fix(fireworks): skip #transform=inline for base64 data URLs
1125350
1 month ago
by awais786-0.31%
Merge branch 'main' into fix/fireworks-base64-image-padding
27894d4
1 month ago
by awais786