A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 12, 21:00 UTC
[Chore] Update `xgrammar` version from 0.1.25 to 0.1.27 (#28221)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
cjackal committed
Nov 20, 2025 at 19:53 UTC
66483a9d00e4e26647dd26b4c49f6eca73972b8c
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -24,7 +24,7 @@ outlines_core == 0.2.11
24
# required for outlines backend disk cache
25
diskcache == 5.6.3
26
lark == 1.2.2
27
-xgrammar == 0.1.25; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64" or platform_machine == "s390x"
27
+xgrammar == 0.1.27; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64" or platform_machine == "s390x"
28
typing_extensions >= 4.10
29
filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
30
partial-json-parser # used for parsing partial JSON outputs