Skip to content

fix(router): discard oldest entry when trimming latency list in lowest_latency strategy #25548

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
krrish-berri-2 merged 3 commits into from
Apr 14, 2026
Merged

fix(router): discard oldest entry when trimming latency list in lowest_latency strategy #25548

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
71f4b0f
fix(router): discard oldest entry when trimming latency list in lowes…
hatim-ez Apr 11, 2026
a6fd5a8
test(router): cover async TTFT trim path in lowest_latency regression…
hatim-ez Apr 11, 2026
d5109e2
format
hatim-ez Apr 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 11 additions & 17 deletions litellm/router_strategy/lowest_latency.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,7 +143,7 @@ def log_success_event( # noqa: PLR0915
else:
request_count_dict[id]["latency"] = request_count_dict[id][
"latency"
][: self.routing_args.max_latency_list_size - 1] + [final_value]
][1:] + [final_value]

## Time to first token
if time_to_first_token is not None:
Expand All @@ -155,13 +155,10 @@ def log_success_event( # noqa: PLR0915
"time_to_first_token", []
).append(time_to_first_token)
else:
request_count_dict[id][
"time_to_first_token"
] = request_count_dict[id]["time_to_first_token"][
: self.routing_args.max_latency_list_size - 1
] + [
time_to_first_token
]
request_count_dict[id]["time_to_first_token"] = (
request_count_dict[id]["time_to_first_token"][1:]
+ [time_to_first_token]
)

if precise_minute not in request_count_dict[id]:
request_count_dict[id][precise_minute] = {}
Expand Down Expand Up @@ -244,7 +241,7 @@ async def async_log_failure_event(self, kwargs, response_obj, start_time, end_ti
else:
request_count_dict[id]["latency"] = request_count_dict[id][
"latency"
][: self.routing_args.max_latency_list_size - 1] + [1000.0]
][1:] + [1000.0]

await self.router_cache.async_set_cache(
key=latency_key,
Expand Down Expand Up @@ -371,7 +368,7 @@ async def async_log_success_event( # noqa: PLR0915
else:
request_count_dict[id]["latency"] = request_count_dict[id][
"latency"
][: self.routing_args.max_latency_list_size - 1] + [final_value]
][1:] + [final_value]

## Time to first token
if time_to_first_token is not None:
Expand All @@ -383,13 +380,10 @@ async def async_log_success_event( # noqa: PLR0915
"time_to_first_token", []
).append(time_to_first_token)
else:
request_count_dict[id][
"time_to_first_token"
] = request_count_dict[id]["time_to_first_token"][
: self.routing_args.max_latency_list_size - 1
] + [
time_to_first_token
]
request_count_dict[id]["time_to_first_token"] = (
request_count_dict[id]["time_to_first_token"][1:]
+ [time_to_first_token]
)

if precise_minute not in request_count_dict[id]:
request_count_dict[id][precise_minute] = {}
Expand Down
Loading
Loading