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 6, 17:00 UTC
[Build] Upgrade xgrammar to get a security fix (#36168)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Mar 14, 2026 at 23:13 UTC
b3debb7e7745d777aa0c2a14cc813a5da2561eb1
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 == 0.1.29; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64" or platform_machine == "s390x" or platform_machine == "ppc64le"
27
+xgrammar >= 0.1.32, < 1.0.0; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64" or platform_machine == "s390x" or platform_machine == "ppc64le"
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