fix: batch-limit stale object cleanup + bump litellm-enterprise to 0.1.37
#25264Comparing
fix/stale-object-cleanup-batch-limit
(caa4b96
) withmain
(7a9a9f0
)0%
- Untouched
- 16
Benchmarks
16 total
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py+1%
546.3 µs541.1 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py+1%
547.3 µs543.3 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
571.3 µs569.3 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
84.3 µs84 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
87.2 µs86.9 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
418.3 µs417.4 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
142.9 µs142.8 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.5 µs87.6 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.3 µs187.5 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.1 µs85.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.8 µs149.1 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.5 µs141.8 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
238.4 µs239.1 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-1%
85.4 µs85.8 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
146.4 µs147.3 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
Commits
Click on a commit to change the comparison rangeBase
main
7a9a9f0
+0.41%
Batch-limit stale managed object cleanup with single bounded SQL query
dd0449c
4 days ago
by ishaan-berri-0.42%
Revert "bump litellm-enterprise to 0.1.37"
caa4b96
3 days ago
by ishaan-berri