[Fix] Add speculative_draft_model_revision to server_args (#5255)

Signed-off-by: Devashish Lal <devashish@rivosinc.com>
This commit is contained in:
DevashishLal-CB
2025-09-05 04:45:46 -07:00
committed by GitHub
parent df97b31f37
commit 13705dae06
13 changed files with 68 additions and 45 deletions

View File

@@ -249,6 +249,7 @@ class ServerArgs:
# Speculative decoding
speculative_algorithm: Optional[str] = None
speculative_draft_model_path: Optional[str] = None
speculative_draft_model_revision: Optional[str] = None
speculative_num_steps: Optional[int] = None
speculative_eagle_topk: Optional[int] = None
speculative_num_draft_tokens: Optional[int] = None
@@ -1498,6 +1499,14 @@ class ServerArgs:
type=str,
help="The path of the draft model weights. This can be a local folder or a Hugging Face repo ID.",
)
parser.add_argument(
"--speculative-draft-model-revision",
type=str,
default=None,
help="The specific draft model version to use. It can be a branch "
"name, a tag name, or a commit id. If unspecified, will use "
"the default version.",
)
parser.add_argument(
"--speculative-num-steps",
type=int,