@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 35b7a05507
Fork 0

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