xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-09 22:17:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Correct an outdated comment. (#24765)

Browse Source 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
This commit is contained in:
Russell Bryant 2025-09-13 03:34:53 -04:00 committed by GitHub
parent 59d7ffc17f
commit 4dad72f0d9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/v1/engine/processor.py
View File

@ -260,10 +260,10 @@ class Processor:
else: else:
# NOTE: engine_level_backend must be "auto" here, because we have # NOTE: engine_level_backend must be "auto" here, because we have
# checked supported_backends above. # checked supported_backends above.
# "auto" is an opt-in to opinionated behavior where we try to # In this mode, we set opinionated defaults based on what we think
# choose a backend based on request contents. This is not the # will satisfy the most use cases without having to worry about
# default as it is less predictable and subject to change # this setting. We include fallback behavior here, but not with any
# between releases as feature support changes. # other setting where a specific backend was specified.
try: try:
validate_xgrammar_grammar(params) validate_xgrammar_grammar(params)
params.guided_decoding.backend = "xgrammar" params.guided_decoding.backend = "xgrammar"