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

Drop vLLM 0.13.0 support (#6069)

Browse Source 
### What this PR does / why we need it?
Drop vLLM 0.13.0 support, upgrade to 0.14.0

- vLLM version: v0.13.0
- vLLM main:
d68209402d

---------

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2026-01-23 09:45:08 +08:00
committed by GitHub
parent 27a513b672
commit 819a4459ce
39 changed files with 86 additions and 272 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm_ascend/attention/context_parallel/mla_cp.py
View File

@@ -12,6 +12,7 @@ from vllm.distributed import (
)
from vllm.forward_context import ForwardContext, get_forward_context
from vllm.utils.math_utils import cdiv
from vllm.v1.attention.backend import AttentionCGSupport
from vllm.v1.kv_cache_interface import AttentionSpec, MLAAttentionSpec
from vllm_ascend.attention.attention_v1 import AscendAttentionState
@@ -37,12 +38,7 @@ from vllm_ascend.attention.context_parallel.common_cp import (
)
from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
from vllm_ascend.compilation.acl_graph import get_draft_graph_params, get_graph_params, update_graph_params_workspaces
from vllm_ascend.utils import vllm_version_is, weak_ref_tensors
if vllm_version_is("0.13.0"):
from vllm.v1.attention.backends.utils import AttentionCGSupport
else:
from vllm.v1.attention.backend import AttentionCGSupport
from vllm_ascend.utils import weak_ref_tensors
MAX_O_PROJ_PREFETCH_SIZE = 16 * 1024 * 1024