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 #10) (#6173)

Browse Source 
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
|`vllm_ascend/ops/layer_shard_linear.py`|
|`vllm_ascend/ops/linear.py`|
|`vllm_ascend/ops/linear_op.py`|
|`vllm_ascend/worker/worker.py`|
| ` vllm_ascend/patch/worker/patch_bert.py` |
| ` vllm_ascend/patch/worker/patch_deepseek.py` |
| ` vllm_ascend/patch/worker/patch_distributed.py` |
| ` vllm_ascend/patch/worker/patch_module.py` |
| ` vllm_ascend/patch/worker/patch_multimodal_merge.py` |
| ` vllm_ascend/patch/worker/patch_qwen3_next.py` |
| ` vllm_ascend/patch/worker/patch_qwen3_next_mtp.py` |
| ` vllm_ascend/patch/worker/patch_rejection_sampler.py` |
| ` vllm_ascend/patch/worker/patch_rope.py` |
| ` vllm_ascend/patch/worker/patch_triton.py` |
| ` vllm_ascend/patch/worker/patch_unquantized_gemm.py` |
| ` vllm_ascend/patch/worker/patch_v2_egale.py` |
|` vllm_ascend/worker/npu_input_batch.py`|
|` vllm_ascend/worker/v2/aclgraph_utils.py`|
|` vllm_ascend/worker/v2/attn_utils.py`|
|` vllm_ascend/worker/v2/model_runner.py`|
|` vllm_ascend/worker/v2/sample/gumbel.py`|
|` vllm_ascend/worker/v2/sample/penalties.py`|
|` vllm_ascend/worker/v2/sample/sampler.py`|
|` vllm_ascend/worker/v2/spec_decode/__init__.py`|
|` vllm_ascend/worker/v2/spec_decode/eagle.py`|
|` vllm_ascend/worker/v2/states.py`|
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.14.0
- vLLM main:
d68209402d

Signed-off-by: MrZ20 <2609716663@qq.com>
Signed-off-by: SILONG ZENG <2609716663@qq.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
SILONG ZENG
2026-02-06 15:35:06 +08:00
committed by GitHub
parent 65b7f716e6
commit 19b5d44ea8
33 changed files with 938 additions and 1243 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
vllm_ascend/worker/v2/attn_utils.py
View File

@@ -18,19 +18,17 @@
#
from collections.abc import Sequence
from typing import Any, Tuple
from typing import Any
import numpy as np
import torch
from vllm.config import VllmConfig
from vllm.v1.kv_cache_interface import EncoderOnlyAttentionSpec, KVCacheConfig
from vllm.v1.attention.backend import AttentionMetadataBuilder
from vllm.v1.kv_cache_interface import EncoderOnlyAttentionSpec, KVCacheConfig
from vllm_ascend.attention.attention_mask import AttentionMaskBuilder
from vllm_ascend.attention.attention_v1 import AscendAttentionState
from vllm_ascend.attention.utils import (AscendCommonAttentionMetadata,
AscendPrefillContextParallelMetadata)
from vllm_ascend.attention.utils import AscendCommonAttentionMetadata, AscendPrefillContextParallelMetadata
_ATTENTION_MASK_BUILDER = None
@@ -59,8 +57,7 @@ def build_attn_metadata(
attn_state: Any | None = None,
graph_pad_size: int = -1,
num_input_tokens: int = 0,
prefill_context_parallel_metadata: AscendPrefillContextParallelMetadata
| None = None,
prefill_context_parallel_metadata: AscendPrefillContextParallelMetadata | None = None,
) -> dict[str, Any]:
"""Build attention metadata for Ascend NPUs."""
# TODO(Ronald1995): optimize AscendCommonAttentionMetadata.
@@ -92,7 +89,8 @@ def build_attn_metadata(
graph_pad_size=graph_pad_size,
num_input_tokens=num_input_tokens,
prefill_context_parallel_metadata=prefill_context_parallel_metadata,
max_seq_len=max_seq_len)
max_seq_len=max_seq_len,
)
attn_metadata_builder = attn_metadata_builders[i]
metadata = attn_metadata_builder.build(
@@ -114,8 +112,8 @@ def build_attn_state(
"""Build attention state for npu's attention backend."""
if vllm_config.model_config.runner_type == "pooling":
if isinstance(
vllm_config.kv_cache_config.kv_cache_groups[0].kv_cache_spec,
EncoderOnlyAttentionSpec,
vllm_config.kv_cache_config.kv_cache_groups[0].kv_cache_spec,
EncoderOnlyAttentionSpec,
):
attn_state = AscendAttentionState.PrefillNoCache
else:
@@ -126,16 +124,14 @@ def build_attn_state(
# but only one token is not hit in cache.
elif np.all(num_scheduled_tokens == 1):
attn_state = AscendAttentionState.DecodeOnly
if (vllm_config.speculative_config
and vllm_config.speculative_config.method == 'mtp'):
if vllm_config.speculative_config and vllm_config.speculative_config.method == "mtp":
# SpecDecoding now supports seq_len=1 and seq_len=2
# In Prefilling Decoding Disaggregation scenario, SpecDecoding
# need to supports seq_len=1
attn_state = AscendAttentionState.SpecDecoding
# Speculative decoding.
elif np.all(num_valid_tokens == 1):
if (vllm_config.speculative_config
and vllm_config.speculative_config.method == 'mtp'):
if vllm_config.speculative_config and vllm_config.speculative_config.method == "mtp":
attn_state = AscendAttentionState.SpecDecoding
else:
attn_state = AscendAttentionState.ChunkedPrefill