Skip to content

[V1][Misc][WIP] Remove Sampler from Model Code #647

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[V1][Misc][WIP] Remove Sampler from Model Code #647

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion vllm_ascend/worker/model_runner_v1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@
from vllm.v1.outputs import EMPTY_MODEL_RUNNER_OUTPUT, ModelRunnerOutput
from vllm.v1.utils import bind_kv_cache
from vllm.v1.worker.gpu_input_batch import CachedRequestState, InputBatch
from vllm.v1.sample.sampler import Sampler

from vllm_ascend.attention.attention import AttentionMaskBuilder
from vllm_ascend.attention.attention_v1 import AscendAttentionState
Expand Down Expand Up @@ -175,6 +176,8 @@ def __init__(self, vllm_config: VllmConfig, device: torch.device):
scheduler_config=self.scheduler_config,
mm_registry=self.mm_registry)

self.sampler = Sampler()

# Lazy initialization
# self.model: nn.Module # Set after load_model
self.kv_caches: List[torch.Tensor] = []
Expand Down Expand Up @@ -645,7 +648,7 @@ def execute_model(

# Sample the next token and get logprobs if needed.
sampling_metadata = self.input_batch.sampling_metadata
sampler_output = self.model.sample(
sampler_output = self.sampler(
logits=logits,
sampling_metadata=sampling_metadata,
)
Expand Down
Loading