[Rust Frontend] Support thinking_token_budget for chat and completions (#46137)

Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: RickyChen / 陳昭儒 <ricky.chen@infinirc.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
This commit is contained in:
Chao-Ju Chen
2026-06-22 16:00:02 +08:00
committed by GitHub
co-authored by Bugen Zhao mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent a9f7b2d41c
commit 80abe0de7d
13 changed files with 178 additions and 7 deletions
@@ -277,6 +277,12 @@ pub struct EngineCoreSamplingParams {
pub max_tokens: u32,
/// Minimum number of tokens to generate before EOS or stop-token handling.
pub min_tokens: u32,
/// Maximum number of reasoning ("thinking") tokens to emit before the
/// reasoning section is force-closed. `None` means unlimited; the
/// user-facing `-1` sentinel is normalized to `None` by the frontend before
/// reaching this DTO, so only non-negative values are sent. Enforced
/// engine-side (and only when a reasoning parser is configured).
pub thinking_token_budget: Option<u64>,
/// Number of log probabilities to return per generated token.
///
/// `None` disables sample logprobs. `-1` requests the full vocabulary.
@@ -345,6 +351,7 @@ impl EngineCoreSamplingParams {
seed: None,
max_tokens: 65536,
min_tokens: 0,
thinking_token_budget: None,
logprobs: None,
prompt_logprobs: None,
min_p: 0.0,
@@ -150,6 +150,7 @@ fn sample_request_with_id(request_id: &str) -> EngineCoreRequest {
top_k: 8,
max_tokens: 32,
min_tokens: 1,
thinking_token_budget: Some(256),
stop_token_ids: vec![151643],
eos_token_id: Some(151645),
all_stop_token_ids: BTreeSet::from([151643, 151645]),
@@ -2502,6 +2503,7 @@ fn python_msgpack_fixtures_match_rust_encoding() {
seed: None,
max_tokens: 16,
min_tokens: 0,
thinking_token_budget: None,
logprobs: None,
prompt_logprobs: None,
min_p: 0.0,
@@ -39,6 +39,7 @@ class EngineCoreSamplingParams(msgspec.Struct, dict=True, omit_defaults=True):
seed: int | None = None
max_tokens: int = 16
min_tokens: int = 0
thinking_token_budget: int | None = None
min_p: float = 0.0
frequency_penalty: float = 0.0
presence_penalty: float = 0.0
@@ -122,6 +123,7 @@ request = EngineCoreRequest(
seed=None,
max_tokens=32,
min_tokens=1,
thinking_token_budget=256,
min_p=0.0,
frequency_penalty=0.0,
presence_penalty=0.0,