Support custom HPA metrics in LiteLLM Helm chart
#29599Comparing
MarshHawk:custom-hpa-autoscaling
(e7f197d
) withlitellm_oss_branch
(5be0797
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py+1%
416.2 µs413.6 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
184.2 µs183.9 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
80.1 µs80.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
143.8 µs144.1 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
137 µs137.3 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
562.5 µs563.6 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.4 µs138.7 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.2 µs82.4 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
142.1 µs142.5 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
234.6 µs235.4 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.9 µs80.2 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
79.1 µs79.4 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py-1%
560.1 µs563.5 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-1%
564.8 µs570 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-2%
80 µs81.4 µs
Commits
Click on a commit to change the comparison rangeBase
main
5be0797
-0.34%
feat: support custom hpa metrics in litellm helm chart
e7f197d
17 hours ago
by MarshHawk