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, 23:30 UTC
[Bugfix] Pin xgrammar to 0.1.11 (#13338)
Michael Goin committed
Feb 15, 2025 at 22:42 UTC
d3d547e057f0ed93531d9356f003ea3e58dcd414
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -20,7 +20,7 @@ tiktoken >= 0.6.0 # Required for DBRX tokenizer
20
lm-format-enforcer >= 0.10.9, < 0.11
21
outlines == 0.1.11
22
lark == 1.2.2
23
-xgrammar >= 0.1.11; platform_machine == "x86_64"
23
+xgrammar == 0.1.11; platform_machine == "x86_64"
24
typing_extensions >= 4.10
25
filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
26
partial-json-parser # used for parsing partial JSON outputs