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 #12) (#6177)

Browse Source 
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
| `vllm_ascend/ops/triton/activation/swiglu_quant.py` |
| `vllm_ascend/ops/triton/batch_invariant/matmul.py` |
| `vllm_ascend/ops/triton/batch_invariant/mean.py` |
| `vllm_ascend/ops/triton/batch_invariant/rmsnorm.py` |
| `vllm_ascend/ops/triton/fla/chunk.py` |
| `vllm_ascend/ops/triton/fla/chunk_delta_h.py` |
| `vllm_ascend/ops/triton/fla/chunk_o.py` |
| `vllm_ascend/ops/triton/fla/chunk_scaled_dot_kkt.py` |
| `vllm_ascend/ops/triton/fla/cumsum.py` |
| `vllm_ascend/ops/triton/fla/fused_qkvzba_split_reshape.py` |
| `vllm_ascend/ops/triton/fla/l2norm.py` |
| `vllm_ascend/ops/triton/fla/layernorm_guard.py` |
| `vllm_ascend/ops/triton/fla/sigmoid_gating.py` |
| `vllm_ascend/ops/triton/fla/solve_tril.py` |
| `vllm_ascend/ops/triton/fla/utils.py` |
| `vllm_ascend/ops/triton/fla/wy_fast.py` |
| `vllm_ascend/ops/triton/fused_gdn_gating.py` |
| `vllm_ascend/ops/triton/layernorm_gated.py` |
| `vllm_ascend/ops/triton/linearnorm/split_qkv_rmsnorm_rope.py` |
| `vllm_ascend/ops/triton/mamba/causal_conv1d.py` |
| `vllm_ascend/ops/triton/reject_sample.py` |
| `vllm_ascend/ops/triton/rope.py` |
| `vllm_ascend/ops/triton/spec_decode/utils.py` |
| `vllm_ascend/ops/triton/triton_utils.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>
This commit is contained in:
SILONG ZENG
2026-01-23 14:59:19 +08:00
committed by GitHub
parent 193acc2c19
commit 78af0c30a3
25 changed files with 760 additions and 996 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
vllm_ascend/ops/triton/fla/utils.py
View File

@@ -9,7 +9,7 @@
# ruff: noqa: E501
import contextlib
import functools
from typing import Callable
from collections.abc import Callable
import torch
from vllm.triton_utils import tl, triton
@@ -19,38 +19,24 @@ def prepare_lens(cu_seqlens: torch.LongTensor) -> torch.LongTensor:
return cu_seqlens[1:] - cu_seqlens[:-1]
def prepare_chunk_indices(cu_seqlens: torch.LongTensor,
chunk_size: int) -> torch.LongTensor:
indices = torch.cat([
torch.arange(n)
for n in triton.cdiv(prepare_lens(cu_seqlens), chunk_size).tolist()
])
return torch.stack([indices.eq(0).cumsum(0) - 1, indices],
1).to(cu_seqlens)
def prepare_chunk_indices(cu_seqlens: torch.LongTensor, chunk_size: int) -> torch.LongTensor:
indices = torch.cat([torch.arange(n) for n in triton.cdiv(prepare_lens(cu_seqlens), chunk_size).tolist()])
return torch.stack([indices.eq(0).cumsum(0) - 1, indices], 1).to(cu_seqlens)
def prepare_chunk_offsets(cu_seqlens: torch.LongTensor,
chunk_size: int) -> torch.LongTensor:
return torch.cat([
cu_seqlens.new_tensor([0]),
triton.cdiv(prepare_lens(cu_seqlens), chunk_size)
]).cumsum(-1)
def prepare_chunk_offsets(cu_seqlens: torch.LongTensor, chunk_size: int) -> torch.LongTensor:
return torch.cat([cu_seqlens.new_tensor([0]), triton.cdiv(prepare_lens(cu_seqlens), chunk_size)]).cumsum(-1)
def input_guard(
fn: Callable[..., torch.Tensor]) -> Callable[..., torch.Tensor]:
def input_guard(fn: Callable[..., torch.Tensor]) -> Callable[..., torch.Tensor]:
"""
A decorator to make sure all input tensors are contiguous and set the device based on input tensors.
"""
@functools.wraps(fn)
def wrapper(*args, **kwargs):
contiguous_args = (i if not isinstance(i, torch.Tensor) else
i.contiguous() for i in args)
contiguous_kwargs = {
k: (v if not isinstance(v, torch.Tensor) else v.contiguous())
for k, v in kwargs.items()
}
contiguous_args = (i if not isinstance(i, torch.Tensor) else i.contiguous() for i in args)
contiguous_kwargs = {k: (v if not isinstance(v, torch.Tensor) else v.contiguous()) for k, v in kwargs.items()}
tensor = None
for arg in args: