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 13, 17:00 UTC
[Structured outputs] Upgrade llguidance to 1.3.0 (#28039)
Signed-off-by: Andy Lo <andy@mistral.ai> Co-authored-by: Russell Bryant <rbryant@redhat.com>
Andy Lo committed
Nov 6, 2025 at 18:24 UTC
5e0c1fe69c516fe4796965185c7d7ca503e44e92
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 == 0.11.3
22
-llguidance >= 0.7.11, < 0.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64" or platform_machine == "s390x"
22
+llguidance >= 1.3.0, < 1.4.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64" or platform_machine == "s390x"
23
outlines_core == 0.2.11
24
# required for outlines backend disk cache
25
diskcache == 5.6.3