[Fix]: Adjust FutureMap's token_id_bufs Size to Prevent ChunkedPrefill's next_token_ids from Overwriting Previous Prefill Requests' next_token_id (#13713)

Signed-off-by: vito.yy <vito.yy@antgroup.com>
2025-11-25 01:08:52 +08:00
parent 1dd9a6ae4d
commit a146f833f1
4 changed files with 24 additions and 7 deletions
@@ -924,7 +924,11 @@ class Scheduler(
        ).stream(self.copy_stream)

        self.future_map = FutureMap(
-            self.max_running_requests, self.device, self.spec_algorithm
+            self.max_running_requests,
+            self.chunked_prefill_size,
+            self.model_config.context_len,
+            self.device,
+            self.spec_algorithm,
        )
        self.batch_record_buf = [None] * 2
        self.batch_record_ct = 0