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

Drop 0.11.0 support (#4377)

Browse Source 
There is a lot hack code for v0.11.0, which makes the code hard to
upgrade to newer vLLM version. Since v0.11.0 will release soon. Let's
drop v0.11.0 support first. Then we'll upgrade to v0.11.2 soon.


- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-11-24 17:08:20 +08:00
committed by GitHub
parent 41ddb06554
commit a1f142b7ad
80 changed files with 467 additions and 1755 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
vllm_ascend/ops/fused_moe/fused_moe.py
View File

@@ -19,7 +19,7 @@ from typing import Any, Callable, Optional
import torch
import torch_npu
from vllm.config import get_current_vllm_config
from vllm.config import CompilationMode, get_current_vllm_config
from vllm.distributed import (get_dp_group, get_ep_group, get_tp_group,
tensor_model_parallel_all_reduce)
from vllm.forward_context import get_forward_context
@@ -28,6 +28,8 @@ from vllm.model_executor.layers.fused_moe.config import FusedMoEConfig
from vllm.model_executor.layers.fused_moe.layer import (
FusedMoE, UnquantizedFusedMoEMethod, determine_expert_map,
get_compressed_expert_map)
from vllm.model_executor.layers.fused_moe.shared_fused_moe import \
SharedFusedMoE
from vllm_ascend.ascend_config import get_ascend_config
from vllm_ascend.ascend_forward_context import MoECommType
@@ -44,17 +46,7 @@ from vllm_ascend.quantization.w8a8_dynamic import \
from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_NZ, enable_sp, is_310p,
is_enable_nz, npu_stream_switch,
shared_expert_dp_enabled,
shared_experts_calculation_stream,
vllm_version_is)
if vllm_version_is("0.11.0"):
from vllm.config import CompilationLevel
from vllm.model_executor.layers.shared_fused_moe import SharedFusedMoE # type: ignore # isort:skip
else:
from vllm.config import CompilationMode
from vllm.model_executor.layers.fused_moe.shared_fused_moe import \
SharedFusedMoE
shared_experts_calculation_stream)
class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
@@ -73,16 +65,9 @@ class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
if ascend_config.torchair_graph_config.enabled:
self.use_aclgraph = False
else:
if vllm_version_is("0.11.0"):
self.use_aclgraph = (
vllm_config.compilation_config.level
== CompilationLevel.PIECEWISE
and not vllm_config.model_config.enforce_eager)
else:
self.use_aclgraph = (
vllm_config.compilation_config.mode
== CompilationMode.VLLM_COMPILE
and not vllm_config.model_config.enforce_eager)
self.use_aclgraph = (vllm_config.compilation_config.mode
== CompilationMode.VLLM_COMPILE and
not vllm_config.model_config.enforce_eager)
self.transpose = True
@@ -209,12 +194,8 @@ class AscendFusedMoE(FusedMoE):
dtype=vllm_config.model_config.dtype)
# init moe.
if vllm_version_is("0.11.0"):
self.local_num_experts, self.expert_map = determine_expert_map(
self.ep_size, self.ep_rank, self.global_num_experts)
else:
self.local_num_experts, self.expert_map, _ = determine_expert_map(
self.ep_size, self.ep_rank, self.global_num_experts)
self.local_num_experts, self.expert_map, _ = determine_expert_map(
self.ep_size, self.ep_rank, self.global_num_experts)
# static eplb initializing with expert_map_path
if self.expert_map_path and os.path.exists(
self.expert_map_path) and os.access(self.expert_map_path,