[Main2Main] Upgrade vLLM to 0226 (#6813)

### What this PR does / why we need it?

Breaking:
1. https://github.com/vllm-project/vllm/pull/33452
2. https://github.com/vllm-project/vllm/pull/33451
3. https://github.com/vllm-project/vllm/pull/32567
4. https://github.com/vllm-project/vllm/pull/32344

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
83b47f67b1

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
Canlin Guo
2026-02-27 16:05:21 +08:00
committed by GitHub
parent 80316c5824
commit e4458b2d2b
40 changed files with 117 additions and 184 deletions

View File

@@ -6,8 +6,6 @@ from vllm.v1.attention.backend import AttentionBackend # type: ignore
from vllm.v1.kv_offload.mediums import CPULoadStoreSpec, GPULoadStoreSpec
from vllm.v1.kv_offload.worker.worker import OffloadingHandler, TransferResult, TransferSpec
from vllm_ascend.utils import vllm_version_is
logger = init_logger(__name__)
@@ -155,30 +153,22 @@ class CpuNpuOffloadingHandler(OffloadingHandler):
def get_finished(self) -> list[TransferResult]:
results: list[TransferResult] = []
if vllm_version_is("v0.15.0"):
for job_id, event in self.transfer_events.items():
if event.query():
results.append((job_id, True))
self.events_pool.append(event)
for job_id, _ in results:
del self.transfer_events[job_id]
else:
finished_job_ids = []
for job_id, event in self.transfer_events.items():
if event.query():
results.append(
TransferResult(
job_id=job_id,
success=True,
transfer_size=None,
transfer_time=None,
transfer_type=None,
)
finished_job_ids = []
for job_id, event in self.transfer_events.items():
if event.query():
results.append(
TransferResult(
job_id=job_id,
success=True,
transfer_size=None,
transfer_time=None,
transfer_type=None,
)
finished_job_ids.append(job_id)
self.events_pool.append(event)
for job_id in finished_job_ids:
del self.transfer_events[job_id]
)
finished_job_ids.append(job_id)
self.events_pool.append(event)
for job_id in finished_job_ids:
del self.transfer_events[job_id]
return results
def wait(self, job_ids: set[int]) -> None: