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 12, 11:00 UTC
Update Transformers pin in CI to 4.57.3 (#29418)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Nov 27, 2025 at 16:42 UTC
e1f262337bcf774032019b5b717a6297a860f190
3 files changed
+3
-3
requirements/nightly_torch_test.txt
+1
-1
@@ -29,7 +29,7 @@ opencv-python-headless >= 4.11.0 # required for video test
29
datamodel_code_generator # required for minicpm3 test
30
lm-eval[api] @ git+https://github.com/EleutherAI/lm-evaluation-harness.git@206b7722158f58c35b7ffcd53b035fdbdda5126d # required for model evaluation test
31
mteb>=1.38.11, <2 # required for mteb test
32
-transformers==4.57.1
32
+transformers==4.57.3
33
tokenizers==0.22.0
34
schemathesis>=3.39.15 # Required for openai schema test.
35
# quantization
requirements/test.in
+1
-1
@@ -37,7 +37,7 @@ datamodel_code_generator # required for minicpm3 test
37
# TODO: Use lm-eval[api]==0.4.10 once released
38
lm-eval[api] @ git+https://github.com/EleutherAI/lm-evaluation-harness.git@206b7722158f58c35b7ffcd53b035fdbdda5126d # required for model evaluation test
39
mteb[bm25s]>=2, <3 # required for mteb test
40
-transformers==4.57.1
40
+transformers==4.57.3
41
tokenizers==0.22.0
42
schemathesis>=3.39.15 # Required for openai schema test.
43
# quantization
requirements/test.txt
+1
-1
@@ -1196,7 +1196,7 @@ tqdm==4.66.6
1196
# transformers
1197
tqdm-multiprocess==0.0.11
1198
# via lm-eval
1199
-transformers==4.57.1
1199
+transformers==4.57.3
1200
# via
1201
# -r requirements/test.in
1202
# genai-perf