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 16, 00:45 UTC
[ci] Upgrade transformers to 4.48.2 in CI dependencies (#12599)
Kevin H. Luu committed
Jan 31, 2025 at 21:22 UTC
35b7a05507e32f6cc60aec7148d3df0c788f7373
3 files changed
+5
-4
requirements-common.txt
+1
-1
@@ -5,7 +5,7 @@ requests >= 2.26.0
5
tqdm
6
blake3
7
py-cpuinfo
8
-transformers >= 4.45.2 # Required for Llama 3.2 and Qwen2-VL.
8
+transformers >= 4.48.2 # Required for Bamba.
9
tokenizers >= 0.19.1 # Required for Llama 3.
10
protobuf # Required by LlamaTokenizer.
11
fastapi >= 0.107.0, < 0.113.0; python_version < '3.9'
requirements-test.in
+1
-1
@@ -27,7 +27,7 @@ matplotlib # required for qwen-vl test
27
mistral_common[opencv] >= 1.5.0 # required for pixtral test
28
datamodel_code_generator # required for minicpm3 test
29
lm-eval[api]==0.4.4 # required for model evaluation test
30
-
30
+transformers==4.48.2
31
# quantization
32
bitsandbytes>=0.45.0
33
buildkite-test-collector==0.1.9
requirements-test.txt
+3
-2
@@ -2,7 +2,7 @@
2
# This file is autogenerated by pip-compile with Python 3.12
3
# by the following command:
4
#
5
-# python3.12 -m piptools compile requirements-test.in -o requirements-test.txt
5
+# python3.12 -m piptools compile requirements-test.in -o requirements-test.txt
6
#
7
absl-py==2.1.0
8
# via rouge-score
@@ -617,8 +617,9 @@ tqdm==4.66.6
617
# transformers
618
tqdm-multiprocess==0.0.11
619
# via lm-eval
620
-transformers==4.47.0
620
+transformers==4.48.2
621
# via
622
+ # -r requirements-test.in
623
# genai-perf
624
# lm-eval
625
# peft