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

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8) (#6604)

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: v0.15.0
- vLLM main:
d7e17aaacd

Signed-off-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
SILONG ZENG
2026-02-07 09:16:07 +08:00
committed by GitHub
parent c63b7a1188
commit 06aa6036f6
17 changed files with 947 additions and 1148 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
vllm_ascend/spec_decode/ngram_proposer.py
View File

@@ -1,13 +1,11 @@
import torch
from vllm.config import CUDAGraphMode
from vllm.v1.spec_decode.ngram_proposer import \
NgramProposer as VllmNgramProposer
from vllm.v1.spec_decode.ngram_proposer import NgramProposer as VllmNgramProposer
from vllm_ascend.spec_decode.interface import Proposer, SpecDcodeType
class NgramProposer(VllmNgramProposer, Proposer):
def __init__(self, vllm_config, device, runner):
super().__init__(vllm_config)
self.name = SpecDcodeType.NGRAM
@@ -19,27 +17,31 @@ class NgramProposer(VllmNgramProposer, Proposer):
pass
@torch.inference_mode()
def dummy_run(self,
num_tokens,
with_prefill=None,
in_graph_capturing=None,
num_reqs=None,
num_tokens_across_dp=None,
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
batch_descriptor=None,
dummy_compute_logits=lambda hidden_states: None,
is_profile=False):
def dummy_run(
self,
num_tokens,
with_prefill=None,
in_graph_capturing=None,
num_reqs=None,
num_tokens_across_dp=None,
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
batch_descriptor=None,
dummy_compute_logits=lambda hidden_states: None,
is_profile=False,
):
pass
def generate_token_ids(self,
valid_sampled_token_ids,
sampling_metadata=None,
scheduler_output=None,
spec_decode_metadata=None,
positions=None,
num_scheduled_tokens=None,
hidden_states=None,
aux_hidden_states=None) -> list[list[int]]:
def generate_token_ids(
self,
valid_sampled_token_ids,
sampling_metadata=None,
scheduler_output=None,
spec_decode_metadata=None,
positions=None,
num_scheduled_tokens=None,
hidden_states=None,
aux_hidden_states=None,
) -> list[list[int]]:
valid_ngram_requests = []
for i, sampled_ids in enumerate(valid_sampled_token_ids):
num_sampled_ids = len(sampled_ids)
@@ -57,8 +59,7 @@ class NgramProposer(VllmNgramProposer, Proposer):
start_idx = self.runner.input_batch.num_tokens_no_spec[i]
end_idx = start_idx + num_sampled_ids
self.runner.input_batch.token_ids_cpu[
i, start_idx:end_idx] = sampled_ids
self.runner.input_batch.token_ids_cpu[i, start_idx:end_idx] = sampled_ids
valid_ngram_requests.append(i)