BerriAI/litellm - CodSpeed

litellm

Blog Docs Changelog

Performance History

No performance history available yetOnce you have some commits, you will be able to see the performance history of your primary branch.

Latest Results

fix(streaming): word-sliced cache replay for stream=true cache hits

michelligabriele:fix/cached-response-streaming-cadence

3 hours ago

fix: fix linting errors

litellm_dev_04_14_2026_p1

4 hours ago

refactor(ui): use antd grid for guardrails monitor metrics Replace Tailwind grid wrappers with antd Row/Col in Guardrails Monitor overview and detail metric sections to keep layout primitives consistent with the ongoing antd migration.

litellm_guardrails-monitor-antd-layout

4 hours ago

test(logging): add tests for get_additional_headers header preservation

litellm_rebuild_ui_cache_breakdown

4 hours ago

fix: fix tool call loop for compression on streaming /v1/messages

litellm_dev_04_14_2026_p1

4 hours ago

refactor(ui): reduce Tremor usage in Guardrails Monitor layout Move Guardrails Monitor overview/detail layout wrappers and section heading components to antd/plain Tailwind while keeping the existing Tremor chart and date picker behavior unchanged for a smaller, low-risk migration step.

litellm_guardrails-monitor-antd-layout

4 hours ago

refactor(ui): reduce Tremor usage in Guardrails Monitor layout Move Guardrails Monitor overview/detail layout wrappers and section heading components to antd/plain Tailwind while keeping the existing Tremor chart and date picker behavior unchanged for a smaller, low-risk migration step.

ryan/guardrails-monitor-antd-layout

4 hours ago

fix(vertex): strip version suffix from model name in count_tokens requests The Vertex AI count-tokens endpoint rejects model names that include version suffixes (@default, @20251001, etc.) with: "claude-sonnet-4-6@default is not supported for token counting" The same model without the suffix ("claude-sonnet-4-6") works correctly. Strip @suffix from both the model parameter and request_data["model"] in handle_count_tokens_request before sending to the API. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

dkindlund:fix/count-tokens-version-suffix

5 hours ago

Latest Branches

0%

fix(streaming): word-sliced cache replay for streaming completions#25670

3 hours ago

199c7a3

michelligabriele:fix/cached-response-streaming-cadence

0%

Prompt Compression - add it to the proxy#25729

4 hours ago

e80f12b

litellm_dev_04_14_2026_p1

0%

refactor(ui): reduce Tremor usage in Guardrails Monitor layout#25803

4 hours ago

48aa776

litellm_guardrails-monitor-antd-layout

© 2026 CodSpeed Technology

Home Terms Privacy Docs