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 14, 05:30 UTC
[Build] Update Xgrammar to 0.1.24 to get a CVE fix (#25188)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Sep 19, 2025 at 02:27 UTC
486c5599e3ab7d721c94dd01e89c87742c01e1ac
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 == 0.1.23; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64"
27
+xgrammar == 0.1.24; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64"
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