xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-02 20:04:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Fix spec decode example (#20296)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-06-30 21:01:48 -07:00 committed by GitHub
parent e28533a16f
commit 7151f92241
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/offline_inference/spec_decode.py
View File

@ -79,9 +79,7 @@ def main():
trust_remote_code=True, trust_remote_code=True,
tensor_parallel_size=args.tp, tensor_parallel_size=args.tp,
enable_chunked_prefill=args.enable_chunked_prefill, enable_chunked_prefill=args.enable_chunked_prefill,
max_num_batched_tokens=args.max_num_batched_tokens,
enforce_eager=args.enforce_eager, enforce_eager=args.enforce_eager,
max_num_seqs=args.max_num_seqs,
gpu_memory_utilization=0.8, gpu_memory_utilization=0.8,
speculative_config=speculative_config, speculative_config=speculative_config,
disable_log_stats=False, disable_log_stats=False,