Remove default values from InitVars so that they're not stored (#29859)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 951445a52d)
This commit is contained in:
committed by
Kevin H. Luu
parent
d8c6210eea
commit
85fb2e3120
@@ -26,16 +26,17 @@ from vllm.v1.worker.tpu_model_runner import (
|
||||
|
||||
|
||||
def get_vllm_config():
|
||||
scheduler_config = SchedulerConfig(
|
||||
max_num_seqs=10,
|
||||
max_num_batched_tokens=512,
|
||||
max_model_len=512,
|
||||
)
|
||||
model_config = ModelConfig(
|
||||
model="facebook/opt-125m",
|
||||
dtype="bfloat16", # TPUs typically use bfloat16
|
||||
seed=42,
|
||||
)
|
||||
scheduler_config = SchedulerConfig(
|
||||
max_num_seqs=10,
|
||||
max_num_batched_tokens=512,
|
||||
max_model_len=512,
|
||||
is_encoder_decoder=model_config.is_encoder_decoder,
|
||||
)
|
||||
cache_config = CacheConfig(
|
||||
block_size=16,
|
||||
gpu_memory_utilization=0.9,
|
||||
|
||||
Reference in New Issue
Block a user