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, 03:30 UTC
[Misc] add xgrammar for arm64 (#18359)
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Prashant Gupta committed
Jul 1, 2025 at 00:02 UTC
22e9d42040f3ecf83da181cfd84ab4cea000c4af
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -23,7 +23,7 @@ lm-format-enforcer >= 0.10.11, < 0.11
23
llguidance >= 0.7.11, < 0.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64"
24
outlines == 0.1.11
25
lark == 1.2.2
26
-xgrammar == 0.1.19; platform_machine == "x86_64" or platform_machine == "aarch64"
26
+xgrammar == 0.1.19; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64"
27
typing_extensions >= 4.10
28
filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
29
partial-json-parser # used for parsing partial JSON outputs