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

[CI] Fix broken CI (#6599)

Browse Source 
Revert
4fb3d5e1b2
it breaks E2E Test

- vLLM version: v0.15.0
- vLLM main:
d7e17aaacd
This commit is contained in:
wangxiyuan
2026-02-06 17:23:58 +08:00
committed by GitHub
parent 19b5d44ea8
commit 06c0aed124
17 changed files with 1147 additions and 947 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
vllm_ascend/spec_decode/interface.py
View File

@@ -1,4 +1,5 @@
import enum
from typing import Optional
import torch
from vllm.config import CUDAGraphMode, VllmConfig
@@ -17,7 +18,11 @@ 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):
@@ -25,29 +30,25 @@ 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: torch.Tensor | None = 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: Optional[torch.Tensor] = 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