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

Upgrade to 0.11.1 newest vllm commit (#3762)

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

c9461e05a4

Fix ```spec decode rejection sampler```, caused by
https://github.com/vllm-project/vllm/pull/26060
Fix some ```import```, caused by
https://github.com/vllm-project/vllm/pull/27374
Fix ```scheduler_config.send_delta_data```, caused by
https://github.com/vllm-project/vllm-ascend/pull/3719
Fix ```init_with_cudagraph_sizes```, caused by
https://github.com/vllm-project/vllm/pull/26016
Fix ```vl model```of replacing PatchEmbed's conv3d to linear layer,
caused by https://github.com/vllm-project/vllm/pull/27418

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.


- vLLM version: v0.11.0rc3
- vLLM main:
c9461e05a4

---------

Signed-off-by: Icey <1790571317@qq.com>
This commit is contained in:
Icey
2025-10-28 14:55:03 +08:00
committed by GitHub
parent f846bd20e4
commit a7450db1bd
12 changed files with 175 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
vllm_ascend/models/qwen2_5_vl.py
View File

@@ -42,7 +42,11 @@ from vllm.model_executor.models.qwen2_5_vl import (
from vllm.model_executor.models.utils import maybe_prefix
from vllm.multimodal import MULTIMODAL_REGISTRY
from vllm_ascend.utils import ACL_FORMAT_FRACTAL_ND, is_enable_nz
from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_ND, is_enable_nz,
vllm_version_is)
if not vllm_version_is("0.11.0"):
from vllm.model_executor.models.vision import conv3d_to_linear_weight
MIN_PAD_SIZE = 64 # min_size to pad weight
MAX_PAD_SIZE = 128 # max_size to pad weight
@@ -355,6 +359,9 @@ class AscendQwen2_5_VisionTransformer(Qwen2_5_VisionTransformer):
params_dict = dict(self.named_parameters(remove_duplicate=False))
loaded_params: Set[str] = set()
for name, loaded_weight in weights:
if not vllm_version_is("0.11.0"):
if name.endswith("patch_embed.proj.weight"):
loaded_weight = conv3d_to_linear_weight(loaded_weight)
for (param_name, weight_name, shard_id) in stacked_params_mapping:
if weight_name not in name:
continue

10
vllm_ascend/models/qwen2_vl.py
View File

@@ -40,7 +40,11 @@ from vllm.model_executor.models.qwen2_vl import (
from vllm.model_executor.models.utils import maybe_prefix
from vllm.multimodal import MULTIMODAL_REGISTRY
from vllm_ascend.utils import ACL_FORMAT_FRACTAL_ND, is_enable_nz
from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_ND, is_enable_nz,
vllm_version_is)
if not vllm_version_is("0.11.0"):
from vllm.model_executor.models.vision import conv3d_to_linear_weight
MIN_PAD_SIZE = 64 # min_size to pad weight
MAX_PAD_SIZE = 128 # max_size to pad weight
@@ -304,6 +308,10 @@ class AscendQwen2VisionTransformer(Qwen2VisionTransformer):
loaded_params: Set[str] = set()
for name, loaded_weight in weights:
if not vllm_version_is("0.11.0"):
if name.endswith("patch_embed.proj.weight"):
loaded_weight = conv3d_to_linear_weight(loaded_weight)
for (param_name, weight_name, shard_id) in stacked_params_mapping:
if weight_name not in name:
continue