fix(config): reject negative max_logprobs (except -1) and long_prefill_token_threshold (#44070)

Signed-off-by: Chenglun Hu <chenglunhu@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
hcl
2026-06-30 04:02:36 +00:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 5b4cb69523
commit af1ee8c475
2 changed files with 2 additions and 2 deletions
+1 -1
View File
@@ -213,7 +213,7 @@ class ModelConfig:
flexibility."""
enable_return_routed_experts: bool = False
"""Whether to return routed experts."""
max_logprobs: int = 20
max_logprobs: int = Field(default=20, ge=-1)
"""Maximum number of log probabilities to return when `logprobs` is
specified in `SamplingParams`. The default value comes the default for the
OpenAI Chat Completions API. -1 means no cap, i.e. all (output_length *
+1 -1
View File
@@ -77,7 +77,7 @@ class SchedulerConfig:
this less than max_num_partial_prefills will allow shorter prompts to jump
the queue in front of longer prompts in some cases, improving latency."""
long_prefill_token_threshold: int = 0
long_prefill_token_threshold: int = Field(default=0, ge=0)
"""For chunked prefill, a request is considered long if the prompt is
longer than this number of tokens."""