Comparing
litellm_guardMainBranch
(38f8d7a
) withmain
(5c1f7d9
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+2%
82.1 µs80.3 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py+1%
569.9 µs564.4 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+1%
81.1 µs80.4 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+1%
79.9 µs79.3 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
235.8 µs236.8 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
415.3 µs413.8 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.9 µs80.1 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
137.9 µs138.2 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
141.4 µs141.6 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
543 µs542.3 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.1 µs82.2 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
541.3 µs541.9 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
137.2 µs137.1 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
182.3 µs182.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144.3 µs144.4 µs
Commits
Click on a commit to change the comparison rangeBase
main
5c1f7d9
+0.2%
[Infra] Guard main branch with PR source-branch check
45d1e1b
4 months ago
by yuneng-berri+0.09%
Also reject PRs from forks, not just non-allowlisted branches
ab71d3d
4 months ago
by yuneng-berri-0.01%
Point contributors toward litellm_oss_branch in guard error messages
38f8d7a
4 months ago
by yuneng-berri