Comparing
litellm_fix/split-service-accounts
(9402485
) withlitellm_internal_staging
(35f6961
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+2%
81.9 µs80.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-2%
144.2 µs147.1 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-2%
136.9 µs139.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
183.9 µs186.3 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py-1%
236.7 µs238.2 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
554.8 µs557.3 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
556.5 µs558.8 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138 µs138.6 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.7 µs414.3 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.2 µs82.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
142.5 µs142.3 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.9 µs80 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
80.9 µs81 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
566.9 µs567.3 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
79.8 µs79.8 µs
Commits
Click on a commit to change the comparison rangeBase
main
35f6961
-0.33%
feat(helm): split per-component ServiceAccounts for gateway, backend, and UI
9402485
3 months ago
by claude