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

[Deprecation][2/N] Replace --task with --runner and --convert (#21470)

Browse Source 
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
2025-07-28 10:42:40 +08:00
committed by GitHub
parent 8f605ee309
commit 86ae693f20
94 changed files with 1117 additions and 1083 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/v1/spec_decode/test_ngram.py
View File

@@ -44,14 +44,7 @@ def test_ngram_proposer():
def ngram_proposer(min_n: int, max_n: int, k: int) -> NgramProposer:
# Dummy model config. Just to set max_model_len.
model_config = ModelConfig(model="facebook/opt-125m",
task="generate",
max_model_len=100,
tokenizer="facebook/opt-125m",
tokenizer_mode="auto",
dtype="auto",
seed=None,
trust_remote_code=False)
model_config = ModelConfig(model="facebook/opt-125m")
return NgramProposer(
vllm_config=VllmConfig(model_config=model_config,
speculative_config=SpeculativeConfig.