Comparing
Anai-Guo:fix/otel-guardrail-mode-list-hashable
(b012ffe
) withlitellm_internal_staging
(79b4578
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-2%
136.7 µs138.8 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py-2%
137.7 µs139.8 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+1%
1.7 ms1.7 ms
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+1%
80.5 µs79.8 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
141.7 µs143.1 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py+1%
183.3 µs181.7 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-1%
143.8 µs144.8 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
80 µs79.7 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.2 µs81.9 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
81.6 µs81.9 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
236.4 µs235.7 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
412.9 µs414.1 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
567.1 µs568.5 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
553.6 µs554.9 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.8 µs79.7 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
555.6 µs556.1 µs
Commits
Click on a commit to change the comparison rangeBase
main
79b4578
-0.1%
fix(opentelemetry): normalize list-valued guardrail_mode for span dedupe (#28486)
b012ffe
3 months ago