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, 06:00 UTC
[MISC] bump huggingface_hub pkg to 0.33.0 (#19547)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Jun 16, 2025 at 20:22 UTC
c3fec47bb7fbed8ac1b8dbaa84f672443b33ed2f
3 files changed
+4
-4
requirements/common.txt
+1
-1
@@ -8,7 +8,7 @@ tqdm
8
blake3
9
py-cpuinfo
10
transformers >= 4.51.1
11
-huggingface-hub[hf_xet] >= 0.32.0 # Required for Xet downloads.
11
+huggingface-hub[hf_xet] >= 0.33.0 # Required for Xet downloads.
12
tokenizers >= 0.21.1 # Required for fast incremental detokenization.
13
protobuf # Required by LlamaTokenizer.
14
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
requirements/test.in
+1
-1
@@ -36,7 +36,7 @@ lm-eval[api]==0.4.8 # required for model evaluation test
36
mteb[bm25s]>=1.38.11, <2 # required for mteb test
37
transformers==4.52.4
38
tokenizers==0.21.1
39
-huggingface-hub[hf_xet]>=0.30.0 # Required for Xet downloads.
39
+huggingface-hub[hf_xet]>=0.33.0 # Required for Xet downloads.
40
schemathesis>=3.39.15 # Required for openai schema test.
41
# quantization
42
bitsandbytes>=0.45.3
requirements/test.txt
+2
-2
@@ -192,7 +192,7 @@ h11==0.14.0
192
# via httpcore
193
harfile==0.3.0
194
# via schemathesis
195
-hf-xet==0.1.4
195
+hf-xet==1.1.3
196
# via huggingface-hub
197
hiredis==3.0.0
198
# via tensorizer
@@ -202,7 +202,7 @@ httpx==0.27.2
202
# via
203
# -r requirements/test.in
204
# schemathesis
205
-huggingface-hub==0.30.1
205
+huggingface-hub==0.33.0
206
# via
207
# -r requirements/test.in
208
# accelerate