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

22
vllm_ascend/torchair/models/qwen3_moe.py
View File

@@ -23,7 +23,7 @@ from torch import nn
from transformers import PretrainedConfig
from vllm.attention import Attention, AttentionMetadata
from vllm.compilation.decorators import support_torch_compile
from vllm.config import CacheConfig, VllmConfig
from vllm.config import CacheConfig, CompilationMode, VllmConfig
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
from vllm.distributed.parallel_state import (get_dp_group, get_ep_group,
get_tp_group)
@@ -55,12 +55,6 @@ from vllm_ascend.attention.attention_v1 import AscendAttentionState
from vllm_ascend.torchair.ops.sequence_parallel import (MetadataForPadding,
init_metadata_for_sp)
from vllm_ascend.torchair.ops.torchair_fused_moe import TorchairAscendFusedMoE
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("0.11.0"):
from vllm.config import CompilationLevel
else:
from vllm.config import CompilationMode
class CustomSparseMoeBlock(Qwen3MoeSparseMoeBlock):
@@ -299,16 +293,10 @@ class CustomQwen3MoeDecoderLayer(Qwen3MoeDecoderLayer):
layer_idx = extract_layer_index(prefix)
mlp_only_layers = ([] if not hasattr(config, "mlp_only_layers") else
config.mlp_only_layers)
if vllm_version_is("0.11.0"):
self.use_aclgraph = (vllm_config is not None
and vllm_config.compilation_config.level
== CompilationLevel.PIECEWISE and
not vllm_config.model_config.enforce_eager)
else:
self.use_aclgraph = (vllm_config is not None
and vllm_config.compilation_config.mode
== CompilationMode.VLLM_COMPILE and
not vllm_config.model_config.enforce_eager)
self.use_aclgraph = (vllm_config is not None
and vllm_config.compilation_config.mode
== CompilationMode.VLLM_COMPILE
and not vllm_config.model_config.enforce_eager)
if (layer_idx not in mlp_only_layers) and (
config.num_experts > 0 and
(layer_idx + 1) % config.decoder_sparse_step == 0):