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

[Main2Main] Upgrade vLLM to 0226 (#6813)

Browse Source 
### 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
Download Patch File Download Diff File Expand all files Collapse all files

15
vllm_ascend/ops/fused_moe/fused_moe.py
View File

@@ -31,7 +31,7 @@ from vllm.model_executor.layers.fused_moe.shared_fused_moe import SharedFusedMoE
from vllm_ascend.utils import vllm_version_is
if not vllm_version_is("0.15.0"):
if not vllm_version_is("0.16.0"):
from vllm.model_executor.layers.fused_moe.fused_moe_method_base import FusedMoEMethodBase # type: ignore
from vllm.model_executor.layers.fused_moe.router.fused_moe_router import FusedMoERouter # type: ignore
from vllm.model_executor.layers.fused_moe.runner.default_moe_runner import DefaultMoERunner # type: ignore
@@ -169,7 +169,7 @@ class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
return final_hidden_states
if not vllm_version_is("0.15.0"):
if not vllm_version_is("0.16.0"):
# Please remove this inheritance after extending vllm, todo(wxs)
class AscendMoERunner(DefaultMoERunner):
"""
@@ -323,10 +323,10 @@ class AscendFusedMoE(FusedMoE):
setup_moe_comm_method(self.moe_config)
self.quant_type = self._get_quant_type()
if not vllm_version_is("0.15.0"):
if not vllm_version_is("0.16.0"):
self.runner = self._init_runner()
if not vllm_version_is("0.15.0"):
if not vllm_version_is("0.16.0"):
def _init_runner(self):
# Storing the runner in the FusedMoE is an intermediate state, eventually
@@ -372,7 +372,7 @@ class AscendFusedMoE(FusedMoE):
"""
return torch.ops.vllm.maybe_all_reduce_tensor_model_parallel(final_hidden_states)
if not vllm_version_is("0.15.0"):
if not vllm_version_is("0.16.0"):
def forward(
self,
@@ -519,8 +519,7 @@ class AscendSharedFusedMoE(SharedFusedMoE, AscendFusedMoE):
):
AscendFusedMoE.__init__(self, **kwargs)
if not vllm_version_is("0.15.0"):
self._routed_input_transform = routed_input_transform
self._routed_input_transform = routed_input_transform
self._shared_experts = shared_experts
self.use_overlapped = use_overlapped
self.shared_expert_stream = None
@@ -533,7 +532,7 @@ class AscendSharedFusedMoE(SharedFusedMoE, AscendFusedMoE):
logger.info_once("Sequence parallelism is enabled, shared experts are replicated for best performance.")
self._gate = gate
if not vllm_version_is("0.15.0"):
if not vllm_version_is("0.16.0"):
# Recreate the runner with the correct shared_experts parameter
# The parent class created the runner before self._shared_experts was set
self.runner = self._init_runner()

22
vllm_ascend/ops/mla.py
View File

@@ -25,18 +25,13 @@ from torch import nn
from vllm.config import CacheConfig, get_current_vllm_config
from vllm.distributed import get_tensor_model_parallel_world_size
from vllm.forward_context import ForwardContext, get_forward_context
from vllm.model_executor.layers.attention import MLAAttention
from vllm.model_executor.layers.mla import MLAModules, MultiHeadLatentAttentionWrapper
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.utils.torch_utils import direct_register_custom_op
from vllm.v1.attention.backend import AttentionMetadata # type: ignore
from vllm_ascend.ascend_config import get_ascend_config
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("v0.15.0"):
from vllm.attention.layer import MLAAttention # type: ignore
else:
from vllm.model_executor.layers.attention import MLAAttention
class IndexerWrapper(nn.Module):
@@ -126,17 +121,16 @@ class AscendMultiHeadLatentAttention(MultiHeadLatentAttentionWrapper):
o_proj=mla_modules.o_proj,
)
if not vllm_version_is("v0.15.0"):
original_process_weights = self.mla_attn.process_weights_after_loading
original_process_weights = self.mla_attn.process_weights_after_loading
def wrapped_process_weights(act_dtype: torch.dtype):
from vllm_ascend.attention.sfa_v1 import AscendSFAImpl
def wrapped_process_weights(act_dtype: torch.dtype):
from vllm_ascend.attention.sfa_v1 import AscendSFAImpl
if not isinstance(self.mla_attn.impl, AscendSFAImpl):
original_process_weights(act_dtype)
self.mla_attn.impl.process_weights_after_loading(act_dtype)
if not isinstance(self.mla_attn.impl, AscendSFAImpl):
original_process_weights(act_dtype)
self.mla_attn.impl.process_weights_after_loading(act_dtype)
self.mla_attn.process_weights_after_loading = wrapped_process_weights
self.mla_attn.process_weights_after_loading = wrapped_process_weights
compilation_config = get_current_vllm_config().compilation_config
if prefix in compilation_config.static_forward_context: