xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-13 07:59:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

MAX_SPEC_LEN

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-08-31 20:43:25 -07:00
parent 22771e5d83
commit ba1a58f51b
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/v1/worker/gpu_worker_states.py
View File

@ -22,6 +22,8 @@ from vllm.v1.sample.logits_processor import LogitsProcessors
from vllm.v1.sample.metadata import SamplingMetadata from vllm.v1.sample.metadata import SamplingMetadata
from vllm.v1.spec_decode.metadata import SpecDecodeMetadata from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
_MAX_SPEC_LEN = 32
@dataclass @dataclass
class RequestData: class RequestData:
@ -323,7 +325,7 @@ class RequestState:
logits_indices, logits_indices,
target_logits_indices, target_logits_indices,
bonus_logits_indices, bonus_logits_indices,
BLOCK_SIZE=triton.next_power_of_2(32 + 1), BLOCK_SIZE=triton.next_power_of_2(_MAX_SPEC_LEN + 1),
) )
draft_token_ids = input_ids[logits_indices] draft_token_ids = input_ids[logits_indices]