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 15, 01:00 UTC
[Misc] bump xgrammar version to v0.1.21 (#20992)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Jul 16, 2025 at 10:42 UTC
b5c3b683590d3a956318dd5d4b29377587bacfed
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -25,7 +25,7 @@ outlines_core == 0.2.10
25
# required for outlines backend disk cache
26
diskcache == 5.6.3
27
lark == 1.2.2
28
-xgrammar == 0.1.19; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64"
28
+xgrammar == 0.1.21; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64"
29
typing_extensions >= 4.10
30
filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
31
partial-json-parser # used for parsing partial JSON outputs