[Bugfix] add compilation/__init__.py to fix import error (#1152)

1. Add `__init__.py` for vllm_ascend/compilation to make sure it's a
python module
2. Fix model runner bug to keep the same with vllm
3. Add release note for 0.9.0rc2

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-06-10 17:14:25 +08:00
committed by GitHub
parent e68e81f2ce
commit b75cb788dd
7 changed files with 23 additions and 10 deletions

View File

View File

@@ -496,7 +496,11 @@ class NPUModelRunner(LoRAModelRunnerMixin):
# Update the block IDs.
if not req_data.resumed_from_preemption:
# Append the new blocks to the existing block IDs.
req_state.block_ids.extend(req_data.new_block_ids)
for block_ids, new_block_ids in zip( # type: ignore[call-overload]
req_state.block_ids,
req_data.new_block_ids,
strict=True):
block_ids.extend(new_block_ids)
else:
# The request is resumed from preemption.
# Replace the existing block IDs with the new ones.