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

47
vllm_ascend/spec_decode/interface.py
View File

@@ -1,5 +1,4 @@
import enum
from typing import Optional
import torch
from vllm.config import CUDAGraphMode, VllmConfig
@@ -18,11 +17,7 @@ class SpecDcodeType(enum.Enum):
class Proposer:
def __init__(self,
vllm_config: VllmConfig,
device: torch.device = None,
runner=None):
def __init__(self, vllm_config: VllmConfig, device: torch.device = None, runner=None):
pass
def load_model(self, model):
@@ -30,25 +25,29 @@ class Proposer:
raise NotImplementedError
@torch.inference_mode()
def dummy_run(self,
num_tokens: int,
with_prefill: bool = False,
in_graph_capturing: bool = False,
num_reqs: int = 0,
num_tokens_across_dp: Optional[torch.Tensor] = None,
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
batch_descriptor=None):
def dummy_run(
self,
num_tokens: int,
with_prefill: bool = False,
in_graph_capturing: bool = False,
num_reqs: int = 0,
num_tokens_across_dp: torch.Tensor | None = None,
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
batch_descriptor=None,
):
"""Called by dummy_run in modle_runner"""
raise NotImplementedError
def generate_token_ids(self,
valid_sampled_token_ids: list[list[int]],
sampling_metadata: SamplingMetadata = None,
scheduler_output: SchedulerOutput = None,
spec_decode_metadata: SpecDecodeMetadata = None,
positions: torch.Tensor = None,
num_scheduled_tokens: int = 0,
hidden_states: torch.Tensor = None,
aux_hidden_states: torch.Tensor = None):
def generate_token_ids(
self,
valid_sampled_token_ids: list[list[int]],
sampling_metadata: SamplingMetadata = None,
scheduler_output: SchedulerOutput = None,
spec_decode_metadata: SpecDecodeMetadata = None,
positions: torch.Tensor = None,
num_scheduled_tokens: int = 0,
hidden_states: torch.Tensor = None,
aux_hidden_states: torch.Tensor = None,
):
"""Called by execute_model in model_runner"""
raise NotImplementedError
raise NotImplementedError