[FlashInfer] Upgrade to 0.2.0 (#11194)
Signed-off-by: Bowen Wang <abmfy@icloud.com> Signed-off-by: youkaichao <youkaichao@gmail.com> Co-authored-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
@@ -114,7 +114,7 @@ def _initialize_model(
|
||||
all_params = [param.name for param in signatures.parameters.values()]
|
||||
if "vllm_config" in all_params and "prefix" in all_params:
|
||||
# new-style model class
|
||||
with set_current_vllm_config(vllm_config):
|
||||
with set_current_vllm_config(vllm_config, check_compile=True):
|
||||
return model_class(vllm_config=vllm_config, prefix=prefix)
|
||||
|
||||
msg = ("vLLM model class should accept `vllm_config` and `prefix` as "
|
||||
@@ -142,7 +142,7 @@ def _initialize_model(
|
||||
kwargs["lora_config"] = vllm_config.lora_config
|
||||
if "scheduler_config" in all_params:
|
||||
kwargs["scheduler_config"] = vllm_config.scheduler_config
|
||||
with set_current_vllm_config(vllm_config):
|
||||
with set_current_vllm_config(vllm_config, check_compile=True):
|
||||
return model_class(**kwargs)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user