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, 14:45 UTC
Update Numba to 0.61.2 (#16376)
Signed-off-by: cyy <cyyever@outlook.com>
cyyever committed
Apr 10, 2025 at 15:59 UTC
ec1f9c8c9160d041c2ad17d60197d1db8adb8b22
4 files changed
+4
-4
requirements/cuda.txt
+1
-1
@@ -2,7 +2,7 @@
2
-r common.txt
3
4
numba == 0.60.0; python_version == '3.9' # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding
5
-numba == 0.61; python_version > '3.9'
5
+numba == 0.61.2; python_version > '3.9'
6
7
# Dependencies for NVIDIA GPUs
8
ray[cgraph]>=2.43.0, !=2.44.* # Ray Compiled Graph, required for pipeline parallelism in V1.
requirements/rocm.txt
+1
-1
@@ -2,7 +2,7 @@
2
-r common.txt
3
4
numba == 0.60.0; python_version == '3.9' # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding
5
-numba == 0.61; python_version > '3.9'
5
+numba == 0.61.2; python_version > '3.9'
6
7
# Dependencies for AMD GPUs
8
awscli
requirements/test.in
+1
-1
@@ -42,7 +42,7 @@ genai_perf==0.0.8
42
tritonclient==2.51.0
43
44
numba == 0.60.0; python_version == '3.9' # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding
45
-numba == 0.61; python_version > '3.9'
45
+numba == 0.61.2; python_version > '3.9'
46
numpy
47
runai-model-streamer==0.11.0
48
runai-model-streamer-s3==0.11.0
requirements/test.txt
+1
-1
@@ -267,7 +267,7 @@ nltk==3.9.1
267
# via rouge-score
268
num2words==0.5.14
269
# via -r requirements/test.in
270
-numba==0.61.0
270
+numba==0.61.2
271
# via
272
# -r requirements/test.in
273
# librosa