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 7, 22:45 UTC
[CI/Build] Fix gRPC version mismatch (#35013)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Feb 22, 2026 at 03:14 UTC
965fe45935473e0a81cc6a0885ae7161b9c8b8cf
3 files changed
+16
-3
requirements/rocm.txt
+6
-2
@@ -1,6 +1,11 @@
1
# Common dependencies
2
-r common.txt
3
4
+# The version of gRPC libraries should be consistent with each other
5
+grpcio==1.78.0
6
+grpcio-reflection==1.78.0
7
+grpcio-tools==1.78.0
8
+
9
numba == 0.61.2 # Required for N-gram speculative decoding
10
11
# Dependencies for AMD GPUs
@@ -14,5 +19,4 @@ setuptools>=77.0.3,<80.0.0
19
setuptools-scm>=8
20
runai-model-streamer[s3,gcs]==0.15.3
21
conch-triton-kernels==1.2.1
17
-timm>=1.0.17
18
-grpcio-tools==1.78.0 # Should match `build.txt`
\ No newline at end of file
22
+timm>=1.0.17
\ No newline at end of file
requirements/test.in
+5
-1
@@ -48,7 +48,11 @@ buildkite-test-collector==0.1.9
48
genai_perf>=0.0.8
49
tritonclient>=2.51.0
50
51
-grpcio-tools==1.78.0 # Should match `build.txt`
51
+# The version of gRPC libraries should be consistent with each other
52
+grpcio==1.78.0
53
+grpcio-reflection==1.78.0
54
+grpcio-tools==1.78.0
55
+
56
arctic-inference == 0.1.1 # Required for suffix decoding test
57
numba == 0.61.2 # Required for N-gram speculative decoding
58
numpy
requirements/test.txt
+5
@@ -287,9 +287,13 @@ greenlet==3.2.3
287
# via sqlalchemy
288
grpcio==1.78.0
289
# via
290
+ # -r requirements/test.in
291
+ # grpcio-reflection
292
# grpcio-tools
293
# ray
294
# tensorboard
295
+grpcio-reflection==1.78.0
296
+ # via -r requirements/test.in
297
grpcio-tools==1.78.0
298
# via -r requirements/test.in
299
h11==0.14.0
@@ -758,6 +762,7 @@ protobuf==6.33.2
762
# via
763
# google-api-core
764
# googleapis-common-protos
765
+ # grpcio-reflection
766
# grpcio-tools
767
# opentelemetry-proto
768
# proto-plus