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

[CI] Remove compatibility maintenance for vllm v0.10.1 and v0.10.1.1 (#2840)

Browse Source 
### What this PR does / why we need it?
Remove compatibility maintenance for vllm v0.10.1 and v0.10.1.1

### Does this PR introduce _any_ user-facing change?
branch main of vllm-ascend will not be compatible with vllm v0.10.1 and
v0.10.1.1

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

- vLLM version: v0.10.1.1
- vLLM main:
6fb2788163

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-09-10 08:43:10 +08:00
committed by GitHub
parent 93e28e6862
commit edf1f600ad
22 changed files with 340 additions and 876 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm_ascend/models/qwen3_moe.py
View File

@@ -51,7 +51,6 @@ from vllm.sequence import IntermediateTensors
from vllm_ascend.ops.fused_moe import AscendFusedMoE
from vllm_ascend.ops.sequence_parallel import (MetadataForPadding,
init_metadata_for_sp)
from vllm_ascend.utils import vllm_version_is
class CustomSparseMoeBlock(Qwen3MoeSparseMoeBlock):
@@ -255,11 +254,8 @@ class CustomQwen3MoeModel(Qwen3MoeModel):
quant_config = vllm_config.quant_config
parallel_config = vllm_config.parallel_config
if vllm_version_is("0.10.1.1") or vllm_version_is("0.10.1"):
self.num_redundant_experts = parallel_config.num_redundant_experts
else:
eplb_config = parallel_config.eplb_config
self.num_redundant_experts = eplb_config.num_redundant_experts
eplb_config = parallel_config.eplb_config
self.num_redundant_experts = eplb_config.num_redundant_experts
self.padding_idx = config.pad_token_id
self.vocab_size = config.vocab_size
self.config = config