[Deprecation][2/N] Replace --task with --runner and --convert (#21470)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-07-27 19:42:40 -07:00
committed by GitHub
co-authored by Harry Mellor
parent 8f605ee309
commit 86ae693f20
94 changed files with 1117 additions and 1083 deletions
+3 -3
View File
@@ -127,8 +127,8 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
self.is_multimodal_model = model_config.is_multimodal_model
self.is_pooling_model = model_config.pooler_config is not None
self.is_encoder_only_model = False
self.model_supports_multimodal_raw_input = (
model_config.model_supports_multimodal_raw_input)
self.is_multimodal_raw_input_supported = (
model_config.is_multimodal_raw_input_supported)
self.max_model_len = model_config.max_model_len
self.max_num_tokens = scheduler_config.max_num_batched_tokens
self.max_num_reqs = scheduler_config.max_num_seqs
@@ -583,7 +583,7 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
) -> dict[str, Any]:
model_kwargs: dict[str, Any] = {}
if self.model_supports_multimodal_raw_input:
if self.is_multimodal_raw_input_supported:
# This model requires the raw multimodal data in input.
if scheduler_output:
multi_modal_kwargs_list = []