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 16, 05:45 UTC
[Core] Require xgrammar >= 0.1.6 (#11021)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Dec 9, 2024 at 11:44 UTC
e691b26f6fae5a3a1c220d15f20de83c7d78ed51
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -19,7 +19,7 @@ prometheus-fastapi-instrumentator >= 7.0.0
19
tiktoken >= 0.6.0 # Required for DBRX tokenizer
20
lm-format-enforcer >= 0.10.9, < 0.11
21
outlines >= 0.0.43, < 0.1
22
-xgrammar >= 0.1.5; platform_machine == "x86_64"
22
+xgrammar >= 0.1.6; platform_machine == "x86_64"
23
typing_extensions >= 4.10
24
filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
25
partial-json-parser # used for parsing partial JSON outputs