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, 11:00 UTC
[V1][Structured Output] Update llguidance (`>= 0.7.11`) to avoid AttributeError (no `StructTag`) (#17839)
Signed-off-by: shen-shanshan <467638484@qq.com>
Shanshan Shen committed
May 9, 2025 at 11:14 UTC
760e3ecc8fa0cee06eff55fe08f91f621d4e2221
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -19,7 +19,7 @@ pillow # Required for image processing
19
prometheus-fastapi-instrumentator >= 7.0.0
20
tiktoken >= 0.6.0 # Required for DBRX tokenizer
21
lm-format-enforcer >= 0.10.11, < 0.11
22
-llguidance >= 0.7.9, < 0.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64"
22
+llguidance >= 0.7.11, < 0.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64"
23
outlines == 0.1.11
24
lark == 1.2.2
25
xgrammar == 0.1.18; platform_machine == "x86_64" or platform_machine == "aarch64"