[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:
0
vllm_ascend/compilation/__init__.py
Normal file
0
vllm_ascend/compilation/__init__.py
Normal 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.
|
||||
|
||||
Reference in New Issue
Block a user