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, 19:45 UTC
[Build/CI] Move ninja to common deps (#14835)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Mar 14, 2025 at 17:25 UTC
233ffce1ebd3a0389c8adfd413de715d4f351d6f
4 files changed
+2
-4
requirements/common.txt
+1
@@ -38,3 +38,4 @@ cloudpickle # allows pickling lambda functions in model_executor/models/registry
38
watchfiles # required for http server to monitor the updates of TLS files
39
python-json-logger # Used by logging as per examples/other/logging_configuration.md
40
scipy # Required for phi-4-multimodal-instruct
41
+ninja # Required for xgrammar, rocm, tpu, xpu
requirements/rocm-build.txt
-1
@@ -7,7 +7,6 @@ torchvision==0.20.1
7
torchaudio==2.5.1
8
9
cmake>=3.26
10
-ninja
10
packaging
11
setuptools>=61
12
setuptools-scm>=8
requirements/tpu.txt
-1
@@ -3,7 +3,6 @@
3
4
# Dependencies for TPU
5
cmake>=3.26
6
-ninja
6
packaging
7
setuptools-scm>=8
8
wheel
requirements/xpu.txt
+1
-2
@@ -3,7 +3,6 @@
3
4
ray>=2.9
5
cmake>=3.26
6
-ninja
6
packaging
7
setuptools-scm>=8
8
setuptools>=75.8.0
@@ -21,4 +20,4 @@ pytorch-triton-xpu
20
# FIXME: This will be fix in ipex 2.7. just leave this here for awareness.
21
# intel-extension-for-pytorch==2.6.10+xpu
22
oneccl_bind_pt==2.6.0+xpu
24
---extra-index-url=https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
\ No newline at end of file
23
+--extra-index-url=https://pytorch-extension.intel.com/release-whl/stable/xpu/us/