[EAGLE] many fixes for eagle (#4195)

Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: Sehoon Kim <sehoon@x.ai>
This commit is contained in:
Lianmin Zheng
2025-03-07 22:12:13 -08:00
parent d052f4c8a9
commit d4017a6b63
15 changed files with 202 additions and 135 deletions

View File

@@ -957,11 +957,13 @@ class Scheduler:
self.req_to_token_pool.free(self.chunked_req.req_pool_idx)
self.batch_is_full = False
# Filter batch
last_bs = self.last_batch.batch_size()
self.last_batch.filter_batch()
if self.last_batch.batch_size() < last_bs:
self.batch_is_full = False
# Merge the new batch into the running batch
if not self.last_batch.is_empty():
if self.running_batch is None:
self.running_batch = self.last_batch