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

Remove default values from InitVars so that they're not stored (#29859)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 951445a52d)
This commit is contained in:
Harry Mellor
2025-12-02 12:16:37 +00:00
committed by Kevin H. Luu
parent d8c6210eea
commit 85fb2e3120
17 changed files with 139 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
tests/v1/worker/test_gpu_model_runner.py
View File

@@ -79,16 +79,17 @@ def initialize_kv_cache(runner: GPUModelRunner):
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="float16",
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=BLOCK_SIZE,
gpu_memory_utilization=0.9,
@@ -784,14 +785,15 @@ def test_hybrid_attention_mamba_tensor_shapes(monkeypatch):
initialize_model_parallel(tensor_model_parallel_size=1)
torch.set_default_dtype(torch.float16)
model_config = ModelConfig(
model="ibm-granite/granite-4.0-tiny-preview",
dtype="float16",
)
scheduler_config = SchedulerConfig(
max_num_seqs=10,
max_num_batched_tokens=512,
max_model_len=512,
)
model_config = ModelConfig(
model="ibm-granite/granite-4.0-tiny-preview",
dtype="float16",
is_encoder_decoder=model_config.is_encoder_decoder,
)
cache_config = CacheConfig(
block_size=BLOCK_SIZE,