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 3, 15:15 UTC
Bump llguidance to 1.7 (#42150)
Signed-off-by: RickyChen / 陳昭儒 <ricky.chen@infinirc.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Chao-Ju Chen committed
May 15, 2026 at 08:35 UTC
0d4d334eaa583b9c09aa4eb7538c22db99fd84b3
2 files changed
+2
-2
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 >= 1.3.0, < 1.4.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64" or platform_machine == "ppc64le"
22
+llguidance >= 1.7.0, < 1.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64" or platform_machine == "ppc64le"
23
outlines_core == 0.2.14
24
# required for outlines backend disk cache
25
diskcache == 5.6.3
requirements/test/rocm.txt
+1
-1
@@ -466,7 +466,7 @@ libnacl==2.1.0
466
# via tensorizer
467
librosa==0.10.2.post1
468
# via -r requirements/test/rocm.in
469
-llguidance==1.3.0
469
+llguidance==1.7.5
470
# via
471
# -c requirements/common.txt
472
# -r requirements/test/../common.txt