xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-04 00:07:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix minor difference

Browse Source 
Signed-off-by: yuantao <2422264527@qq.com>
This commit is contained in:
yuantao 2025-12-22 22:51:34 +08:00
parent cf58a62099
commit 049d2aad0c
2 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/v1/worker/gpu_model_runner.py
View File

@ -5074,7 +5074,6 @@ class GPUModelRunner(
logitsprocs_need_output_token_ids=self.input_batch.logitsprocs_need_output_token_ids,
is_pooling_model=self.is_pooling_model,
num_speculative_tokens=self.num_spec_tokens,
# sink_len=self.sink_len,
)
def _allocate_kv_cache_tensors(

4
vllm/v1/worker/kv_connector_model_runner_mixin.py
View File

@ -200,7 +200,7 @@ class KVConnectorModelRunnerMixin:
try:
kv_cache_stride_order = attn_backend.get_kv_cache_stride_order(
include_num_layers_dimension=True,
include_num_layers_dimension=True
)
except (AttributeError, NotImplementedError):
return False
@ -270,7 +270,7 @@ class KVConnectorModelRunnerMixin:
try:
kv_cache_stride_order = attn_backend.get_kv_cache_stride_order(
include_num_layers_dimension=True,
include_num_layers_dimension=True
)
assert len(kv_cache_stride_order) == len(kv_cache_shape)
except (AttributeError, NotImplementedError):