EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Main2Main] Upgrade vllm commit to 0123 (#6169)

Browse Source 
### What this PR does / why we need it?
1. ✅ Upgrade vllm commit to: 0115
(8471b27df97c3eb79f891802fc0e858f8f7ac6a0)
Modify import paths due to the refactors：
https://github.com/vllm-project/vllm/pull/32245
https://github.com/vllm-project/vllm/pull/32060
Test result:
https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913
2. ✅Upgrade vllm commit to: 0119
(9a1f16da1e423ede2c2f52a9850cbfbb39cefe96)
Fix `WorkerProc.__init__() missing 1 required positional argument:
'is_driver_worker'` due to
https://github.com/vllm-project/vllm/pull/28506
Test result:
https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569
3. ✅Upgrade vllm commit to:
0120(148117ea2e689cd43df4be6892671a17cdae5833)
1. Add `skip_compiled` param in `set_forward_context` due to
https://github.com/vllm-project/vllm/pull/30385
2. Modify `tests/ut/spec_decode/test_eagle_proposer.py` due to
https://github.com/vllm-project/vllm/pull/24322
change `self.max_num_tokens =
vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size`
3. Modify UT import paths due to the
refactors：https://github.com/vllm-project/vllm/pull/32060
Test result:
https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946
4. ✅Upgrade vllm commit to:
0121(f23fb5a7c1b61350c5c40ca1115d3bf8cf2b8cc9)
1. vLLM switched `uses_mrope` from target to draft model config, making
`positions`/`mrope_positions` mutually exclusive, breaking vllm-ascend's
direct self.positions access and tests missing
`draft_model_config.uses_mrope`.
https://github.com/vllm-project/vllm/pull/32048
2. Moved bs_to_padded_graph_size from CompilationConfig to
CudagraphDispatcher due to the refactor
https://github.com/vllm-project/vllm/pull/30143
3. Remove unused `maybe_setup_kv_connector` due to
https://github.com/vllm-project/vllm/pull/32077
Test result:
https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834
6. ✅Upgrade vllm commit to:
0122(8ebf271bb6d1e7e9b1a55be73d755ef1a57dbbe5)
Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig
due to https://github.com/vllm-project/vllm/pull/32414
Test result:
https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054
8. ✅Upgrade vllm commit to:
0123(dc917cceb877dfd13f98c538c4c96158047d98bd)
Setting temperature=0.0 due to the removal of the default temperature
value in https://github.com/vllm-project/vllm/pull/32723
Test result:
https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.14.0
- vLLM main:
d68209402d

---------

Signed-off-by: wjunLu <wjunlu217@gmail.com>
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
Co-authored-by: wjunLu <wjunlu217@gmail.com>
This commit is contained in:
meihanc
2026-01-27 08:44:36 +08:00
committed by GitHub
parent 9780a995e1
commit fea197ad50
25 changed files with 173 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
vllm_ascend/patch/platform/patch_multiproc_executor.py
View File

@@ -19,6 +19,8 @@ from vllm.v1.executor.multiproc_executor import (
set_multiprocessing_worker_envs,
)
from vllm_ascend.utils import vllm_version_is
class AscendMultiprocExecutor(MultiprocExecutor):
def _init_executor(self) -> None:
@@ -29,16 +31,7 @@ class AscendMultiprocExecutor(MultiprocExecutor):
self.shutdown_event = threading.Event()
self.failure_callback: FailureCallback | None = None
self.world_size = self.parallel_config.world_size
assert self.world_size % self.parallel_config.nnodes_within_dp == 0, (
f"global world_size ({self.parallel_config.world_size}) must be "
f"divisible by nnodes_within_dp "
f"({self.parallel_config.nnodes_within_dp}). "
)
self.local_world_size = self.parallel_config.local_world_size
tensor_parallel_size = self.parallel_config.tensor_parallel_size
pp_parallel_size = self.parallel_config.pipeline_parallel_size
pcp_parallel_size = self.parallel_config.prefill_context_parallel_size
tensor_parallel_size, pp_parallel_size, pcp_parallel_size = self._get_parallel_sizes()
assert self.world_size == tensor_parallel_size * pp_parallel_size * pcp_parallel_size, (
f"world_size ({self.world_size}) must be equal to the "
f"tensor_parallel_size ({tensor_parallel_size}) x pipeline"
@@ -77,6 +70,7 @@ class AscendMultiprocExecutor(MultiprocExecutor):
global_start_rank = self.local_world_size * self.parallel_config.node_rank_within_dp
for local_rank in range(self.local_world_size):
global_rank = global_start_rank + local_rank
is_driver_worker = self._is_driver_worker(global_rank)
unready_workers.append(
AscendWorkerProc.make_worker_process(
vllm_config=self.vllm_config,
@@ -85,6 +79,7 @@ class AscendMultiprocExecutor(MultiprocExecutor):
distributed_init_method=distributed_init_method,
input_shm_handle=scheduler_output_handle,
shared_worker_lock=shared_worker_lock,
is_driver_worker=is_driver_worker,
)
)
@@ -120,6 +115,9 @@ class AscendMultiprocExecutor(MultiprocExecutor):
# Wait for all remote response mqs to be ready.
for response_mq in self.response_mqs:
response_mq.wait_until_ready()
self.futures_queue = deque[tuple[FutureWrapper, Callable]]()
self._post_init_executor()
success = True
finally:
if not success:
@@ -130,10 +128,27 @@ class AscendMultiprocExecutor(MultiprocExecutor):
uw.death_writer.close()
self._ensure_worker_termination([uw.proc for uw in unready_workers])
self.futures_queue = deque[tuple[FutureWrapper, Callable]]()
self.output_rank = self._get_output_rank()
def _get_parallel_sizes(self) -> tuple[int, int, int]:
self.world_size = self.parallel_config.world_size
assert self.world_size % self.parallel_config.nnodes_within_dp == 0, (
f"global world_size ({self.parallel_config.world_size}) must be "
f"divisible by nnodes_within_dp "
f"({self.parallel_config.nnodes_within_dp}). "
)
self.local_world_size = self.parallel_config.local_world_size
tp_size = self.parallel_config.tensor_parallel_size
pp_size = self.parallel_config.pipeline_parallel_size
pcp_size = self.parallel_config.prefill_context_parallel_size
return tp_size, pp_size, pcp_size
def _post_init_executor(self) -> None:
pass
def _is_driver_worker(self, rank: int) -> bool:
return rank % self.parallel_config.tensor_parallel_size == 0
class AscendWorkerProc(WorkerProc):
@staticmethod
@@ -144,6 +159,7 @@ class AscendWorkerProc(WorkerProc):
distributed_init_method: str,
input_shm_handle, # Receive SchedulerOutput
shared_worker_lock: LockType,
is_driver_worker: bool = False,
) -> UnreadyWorkerProcHandle:
context = get_mp_context()
# (reader, writer)
@@ -162,6 +178,8 @@ class AscendWorkerProc(WorkerProc):
"death_pipe": death_reader,
"shared_worker_lock": shared_worker_lock,
}
if not vllm_version_is("0.14.1"):
process_kwargs["is_driver_worker"] = is_driver_worker
# Run EngineCore busy loop in background process.
proc = context.Process(
target=WorkerProc.worker_main,