xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 09:06:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Parse SpeculativeConfig Error (#25142)

Browse Source 
Signed-off-by: zxw <1020938856@qq.com>
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:
yyzxw 2025-09-25 19:09:39 +08:00 committed by GitHub
parent 12c1287d64
commit eaeca3cd7f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
vllm/engine/arg_utils.py
View File

@ -1465,12 +1465,18 @@ class EngineArgs:
return False
# V1 supports N-gram, Medusa, and Eagle speculative decoding.
if (self.speculative_config is not None
and self.speculative_config.get("method") == "draft_model"):
raise NotImplementedError(
"Speculative decoding with draft model is not supported yet. "
"Please consider using other speculative decoding methods "
"such as ngram, medusa, eagle, or deepseek_mtp.")
if self.speculative_config is not None:
# speculative_config could still be a dict at this point
if isinstance(self.speculative_config, dict):
method = self.speculative_config.get("method", None)
else:
method = self.speculative_config.method
if method == "draft_model":
raise NotImplementedError(
"Draft model speculative decoding is not supported yet. "
"Please consider using other speculative decoding methods "
"such as ngram, medusa, eagle, or deepseek_mtp.")
V1_BACKENDS = [
"FLASH_ATTN_VLLM_V1",