Comparing
anilmurty:add-tokenjam-callback
(65b3726
) withlitellm_oss_staging
(7af0f05
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+1%
1.7 ms1.7 ms
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
81 µs81.6 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py+1%
184.2 µs183.3 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
136.9 µs137.6 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
79.5 µs79.1 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
540.9 µs543.5 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
141.9 µs142.5 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
235.5 µs236.3 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
565.5 µs563.8 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.1 µs82.3 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.9 µs80 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
412.7 µs412.3 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.1 µs138 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
80.1 µs80.1 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
543.1 µs543.4 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144.2 µs144.3 µs
Commits
Click on a commit to change the comparison rangeBase
main
7af0f05
+0.05%
feat(integrations): Add TokenJam as named callback
280da25
3 months ago
by anilmurty-0.08%
fix(tokenjam): offload sync hooks to executor on async path; lazy logger formatting
65b3726
3 months ago
by anilmurty