[Feature] Mask Replay (#49577)

Signed-off-by: vx120 <893600387@qq.com>
Signed-off-by: vx120 <57470515+vx120@users.noreply.github.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
vx120
2026-08-13 08:44:31 +00:00
committed by GitHub
co-authored by aoshen02 Codex Claude Opus 4.6 OpenAI Codex
parent 10bcad2523
commit 50ba4bc6b2
24 changed files with 557 additions and 6 deletions
+11
View File
@@ -108,6 +108,17 @@ class InputProcessor:
self.tokenizer,
)
if self.model_config.return_sampling_mask:
if params.temperature <= 0:
raise ValueError(
"sampling distribution replay requires temperature > 0"
)
if params.top_k <= 0:
raise ValueError(
"sampling distribution replay requires top_k > 0 to "
"bound sampling mask size, reduce transfer overhead, "
"and avoid potential OOMs"
)
if params.thinking_token_budget is not None and (
self.vllm_config.reasoning_config is None
or not self.vllm_config.reasoning_config.enabled