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 10, 21:30 UTC
[ROCm] Migrate xgrammar to upstream release (#31327)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Dec 28, 2025 at 02:08 UTC
573dd0e6f0897272d498cbb134d40b661f8ae384
2 files changed
+1
-5
requirements/common.txt
+1
-1
@@ -24,7 +24,7 @@ outlines_core == 0.2.11
24
# required for outlines backend disk cache
25
diskcache == 5.6.3
26
lark == 1.2.2
27
-xgrammar == 0.1.27; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64" or platform_machine == "s390x" or platform_machine == "ppc64le"
27
+xgrammar == 0.1.29; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64" or platform_machine == "s390x" or platform_machine == "ppc64le"
28
typing_extensions >= 4.10
29
filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
30
partial-json-parser # used for parsing partial JSON outputs
requirements/rocm-test.txt
-4
@@ -74,10 +74,6 @@ torchgeo==0.7.0
74
# MTEB Benchmark Test
75
mteb==2.1.2
76
77
-# Data processing
78
-xgrammar @ git+https://github.com/divakar-amd/xgrammar@3272f7c520564858056a60480d5afdf69ae79c84
79
-# Test async scheduling
80
-
77
# Utilities
78
num2words==0.5.14
79
# via lm-eval