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

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #8) (#6129)

Browse Source 
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
| vllm_ascend/ops/\_\_init\_\_.py |
| vllm_ascend/ops/activation.py |
| vllm_ascend/ops/flashcomm2_oshard_manager.py |
| vllm_ascend/ops/layernorm.py |
| vllm_ascend/ops/mla.py |
| vllm_ascend/ops/mm_encoder_attention.py |
| vllm_ascend/ops/register_custom_ops.py |
| vllm_ascend/ops/vocab_parallel_embedding.py |
| vllm_ascend/ops/weight_prefetch.py |
| vllm_ascend/spec_decode/\_\_init\_\_.py |
| vllm_ascend/spec_decode/eagle_proposer.py |
| vllm_ascend/spec_decode/interface.py |
| vllm_ascend/spec_decode/mtp_proposer.py |
| vllm_ascend/spec_decode/ngram_proposer.py |
| vllm_ascend/spec_decode/suffix_proposer.py |

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

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

Signed-off-by: MrZ20 <2609716663@qq.com>
Signed-off-by: SILONG ZENG <2609716663@qq.com>
This commit is contained in:
SILONG ZENG
2026-02-06 15:25:08 +08:00
committed by GitHub
parent 99aedaff63
commit 4fb3d5e1b2
17 changed files with 948 additions and 1147 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
vllm_ascend/ops/__init__.py
View File

@@ -27,8 +27,7 @@ if HAS_TRITON:
import vllm_ascend.ops.vocab_parallel_embedding # noqa
from vllm_ascend.ops.activation import AscendQuickGELU, AscendSiluAndMul
from vllm_ascend.ops.rotary_embedding import (
AscendDeepseekScalingRotaryEmbedding, AscendRotaryEmbedding)
from vllm_ascend.ops.rotary_embedding import AscendDeepseekScalingRotaryEmbedding, AscendRotaryEmbedding
class dummyFusionOp:
@@ -40,23 +39,13 @@ class dummyFusionOp:
def register_dummy_fusion_op() -> None:
torch.ops._C_ascend.rms_norm = dummyFusionOp(name="rms_norm")
torch.ops._C_ascend.fused_add_rms_norm = dummyFusionOp(
name="fused_add_rms_norm")
torch.ops._C_ascend.static_scaled_fp8_quant = dummyFusionOp(
name="static_scaled_fp8_quant")
torch.ops._C_ascend.dynamic_scaled_fp8_quant = dummyFusionOp(
name="dynamic_scaled_fp8_quant")
torch.ops._C_ascend.dynamic_per_token_scaled_fp8_quant = dummyFusionOp(
name="dynamic_per_token_scaled_fp8_quant")
torch.ops._C_ascend.rms_norm_static_fp8_quant = dummyFusionOp(
name="rms_norm_static_fp8_quant")
torch.ops._C_ascend.fused_add_rms_norm_static_fp8_quant = dummyFusionOp(
name="fused_add_rms_norm_static_fp8_quant")
torch.ops._C_ascend.rms_norm_dynamic_per_token_quant = dummyFusionOp(
name="rms_norm_dynamic_per_token_quant")
torch.ops._C_ascend.fused_add_rms_norm = dummyFusionOp(name="fused_add_rms_norm")
torch.ops._C_ascend.static_scaled_fp8_quant = dummyFusionOp(name="static_scaled_fp8_quant")
torch.ops._C_ascend.dynamic_scaled_fp8_quant = dummyFusionOp(name="dynamic_scaled_fp8_quant")
torch.ops._C_ascend.dynamic_per_token_scaled_fp8_quant = dummyFusionOp(name="dynamic_per_token_scaled_fp8_quant")
torch.ops._C_ascend.rms_norm_static_fp8_quant = dummyFusionOp(name="rms_norm_static_fp8_quant")
torch.ops._C_ascend.fused_add_rms_norm_static_fp8_quant = dummyFusionOp(name="fused_add_rms_norm_static_fp8_quant")
torch.ops._C_ascend.rms_norm_dynamic_per_token_quant = dummyFusionOp(name="rms_norm_dynamic_per_token_quant")
__all__ = [
"AscendQuickGELU", "AscendSiluAndMul", "AscendRotaryEmbedding",
"AscendDeepseekScalingRotaryEmbedding"
]
__all__ = ["AscendQuickGELU", "AscendSiluAndMul", "AscendRotaryEmbedding", "AscendDeepseekScalingRotaryEmbedding"]