We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent f03850f commit cd5faa9Copy full SHA for cd5faa9
vllm_ascend/sample/rejection_sampler.py
@@ -3,6 +3,7 @@
3
4
import torch
5
import torch.nn as nn
6
+import vllm.v1.sample.rejection_sampler as rs
7
from vllm.logger import init_logger
8
from vllm.v1.sample.metadata import SamplingMetadata
9
from vllm.v1.sample.rejection_sampler import (RejectionSampler, compute_probs,
@@ -450,3 +451,5 @@ def sample_recovered_tokens_pytorch(
450
451
452
if IS_NGRAM:
453
target_probs[token_idx, draft_token_id] = orig_prob
454
+
455
+rs.expand_batch_to_tokens = expand_batch_to_tokens
0 commit comments