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 14, 05:30 UTC
Update `hf_xet` pin to resolve hangs (#22356)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Aug 7, 2025 at 04:31 UTC
ecbea55ca254186ed6cbf62702242d73c177a75f
4 files changed
+1
-5
requirements/common.txt
-1
@@ -8,7 +8,6 @@ tqdm
8
blake3
9
py-cpuinfo
10
transformers >= 4.55.0
11
-huggingface-hub[hf_xet] >= 0.33.0 # Required for Xet downloads.
11
tokenizers >= 0.21.1 # Required for fast incremental detokenization.
12
protobuf # Required by LlamaTokenizer.
13
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
requirements/nightly_torch_test.txt
-1
@@ -31,7 +31,6 @@ lm-eval[api]==0.4.8 # required for model evaluation test
31
mteb>=1.38.11, <2 # required for mteb test
32
transformers==4.52.4
33
tokenizers==0.21.1
34
-huggingface-hub[hf_xet]>=0.30.0 # Required for Xet downloads.
34
schemathesis>=3.39.15 # Required for openai schema test.
35
# quantization
36
bitsandbytes>=0.46.1
requirements/test.in
-1
@@ -37,7 +37,6 @@ lm-eval[api]==0.4.8 # required for model evaluation test
37
mteb[bm25s]>=1.38.11, <2 # required for mteb test
38
transformers==4.55.0
39
tokenizers==0.21.1
40
-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==0.46.1
requirements/test.txt
+1
-2
@@ -276,7 +276,7 @@ h5py==3.13.0
276
# via terratorch
277
harfile==0.3.0
278
# via schemathesis
279
-hf-xet==1.1.3
279
+hf-xet==1.1.7
280
# via huggingface-hub
281
hiredis==3.0.0
282
# via tensorizer
@@ -288,7 +288,6 @@ httpx==0.27.2
288
# schemathesis
289
huggingface-hub==0.34.3
290
# via
291
- # -r requirements/test.in
291
# accelerate
292
# datasets
293
# evaluate