biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Core] Remove unused num_tokens parameter from _init_model_kwargs (#31517)

Browse Source 
Signed-off-by: maang <maang_h@163.com>
This commit is contained in:
maang-h
2025-12-31 12:47:23 +08:00
committed by GitHub
parent 70e1acefcd
commit b4bb5f312f
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/v1/worker/gpu_model_runner.py
View File

@@ -684,7 +684,7 @@ class GPUModelRunner(
with_numpy=numpy,
)
def _init_model_kwargs(self, num_tokens: int):
def _init_model_kwargs(self):
model_kwargs = dict[str, Any]()
if not self.is_pooling_model:
@@ -2579,7 +2579,7 @@ class GPUModelRunner(
input_ids, inputs_embeds = self._prepare_mm_inputs(num_input_tokens)
model_kwargs = {
**self._init_model_kwargs(num_scheduled_tokens),
**self._init_model_kwargs(),
**self._extract_mm_kwargs(scheduler_output),
}
elif self.enable_prompt_embeds and is_first_rank:
@@ -2607,7 +2607,7 @@ class GPUModelRunner(
self.inputs_embeds.gpu[token_ids_idx] = tokens_to_embeds
inputs_embeds = self.inputs_embeds.gpu[:num_input_tokens]
model_kwargs = self._init_model_kwargs(num_input_tokens)
model_kwargs = self._init_model_kwargs()
input_ids = None
else:
# For text-only models, we use token ids as input.
@@ -2616,7 +2616,7 @@ class GPUModelRunner(
# then the embedding layer is not included in the CUDA graph.
input_ids = self.input_ids.gpu[:num_input_tokens]
inputs_embeds = None
model_kwargs = self._init_model_kwargs(num_input_tokens)
model_kwargs = self._init_model_kwargs()
if self.uses_mrope:
positions = self.mrope_positions.gpu[:, :num_input_tokens]
@@ -4293,7 +4293,7 @@ class GPUModelRunner(
):
# Make sure padding doesn't exceed max_num_tokens
assert num_tokens_padded <= self.max_num_tokens
model_kwargs = self._init_model_kwargs(num_tokens_padded)
model_kwargs = self._init_model_kwargs()
if self.supports_mm_inputs and not self.model_config.is_encoder_decoder:
input_ids, inputs_embeds = self._prepare_mm_inputs(num_tokens_padded)
@@ -4304,7 +4304,7 @@ class GPUModelRunner(
elif self.enable_prompt_embeds:
input_ids = None
inputs_embeds = self.inputs_embeds.gpu[:num_tokens_padded]
model_kwargs = self._init_model_kwargs(num_tokens_padded)
model_kwargs = self._init_model_kwargs()
else:
input_ids = self.input_ids.gpu[:num_tokens_padded]
inputs_embeds = None