[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
+2 -10
View File
@@ -695,11 +695,7 @@ def test_estimate_max_model_len(model_id, max_model_len,
# Create a VllmConfig
model_config = ModelConfig(
model_id,
task="generate",
tokenizer=model_id,
tokenizer_mode="auto",
trust_remote_code=False,
seed=0,
runner="generate",
dtype="float16",
max_model_len=max_model_len,
)
@@ -733,11 +729,7 @@ def test_get_max_concurrency_for_kv_cache_config():
max_model_len = 16384
model_config = ModelConfig(
model_id,
task="generate",
tokenizer=model_id,
tokenizer_mode="auto",
trust_remote_code=False,
seed=0,
runner="generate",
dtype="float16",
max_model_len=max_model_len,
)
-3
View File
@@ -1248,9 +1248,6 @@ def create_scheduler_with_priority(
)
model_config = ModelConfig(
model=model,
task="auto",
tokenizer=model,
tokenizer_mode="auto",
trust_remote_code=True,
dtype="float16",
seed=42,
-3
View File
@@ -59,9 +59,6 @@ def create_scheduler(
)
model_config = ModelConfig(
model=model,
task="auto",
tokenizer=model,
tokenizer_mode="auto",
trust_remote_code=True,
dtype="float16",
seed=42,