[V0][V1][Core] Add outlines integration for V1, and update V0 integration. (#15975)

Signed-off-by: Nathan Hoos <thwackyy.y@gmail.com>
This commit is contained in:
Nathan Hoos
2025-07-10 15:30:26 -04:00
committed by GitHub
parent 5e53c89a74
commit d6902ce79f
13 changed files with 804 additions and 461 deletions
+7
View File
@@ -117,6 +117,7 @@ if TYPE_CHECKING:
VLLM_RANDOMIZE_DP_DUMMY_INPUTS: bool = False
VLLM_MARLIN_USE_ATOMIC_ADD: bool = False
VLLM_V0_USE_OUTLINES_CACHE: bool = False
VLLM_V1_USE_OUTLINES_CACHE: bool = False
VLLM_TPU_BUCKET_PADDING_GAP: int = 0
VLLM_TPU_MOST_MODEL_LEN: Optional[int] = None
VLLM_USE_DEEP_GEMM: bool = False
@@ -847,6 +848,12 @@ environment_variables: dict[str, Callable[[], Any]] = {
"VLLM_V0_USE_OUTLINES_CACHE":
lambda: os.environ.get("VLLM_V0_USE_OUTLINES_CACHE", "0") == "1",
# Whether to turn on the outlines cache for V1
# This cache is unbounded and on disk, so it's not safe to use in
# an environment with potentially malicious users.
"VLLM_V1_USE_OUTLINES_CACHE":
lambda: os.environ.get("VLLM_V1_USE_OUTLINES_CACHE", "0") == "1",
# Gap between padding buckets for the forward pass. So we have
# 8, we will run forward pass with [16, 24, 32, ...].
"VLLM_TPU_BUCKET_PADDING_GAP":