Comparing
litellm_vertex-batch-output-transformation
(e3eb1b5
) withlitellm_internal_staging
(e64d98f
)-1%
- Untouched
- 16
Benchmarks
16 total
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py-3%
79.8 µs82 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py-3%
82.1 µs84.2 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-2%
137.4 µs140.8 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-2%
144.4 µs147.2 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-2%
141.7 µs144.3 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py-1%
138.1 µs140.2 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-1%
81.3 µs82.4 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
81.6 µs82.7 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
183.9 µs185.8 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
81.3 µs82 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py-1%
236.6 µs238 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
541.8 µs544.1 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
540.8 µs542.1 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
568.4 µs567.5 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.1 µs413.7 µs
Commits
Click on a commit to change the comparison rangeBase
main
e64d98f
-0.51%
feat(vertex-ai): transform batch prediction outputs to OpenAI format
f6d5502
4 months ago
by Sameerlite-0.17%
fix: address Greptile review comments
380c14e
4 months ago
by Sameerlite-0.49%
Fix greptile review
e3eb1b5
4 months ago
by Sameerlite