@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / e691b26f6f
Fork 0

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