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, 16:00 UTC
Fix `huggingface-cli[hf-xet]` -> `huggingface-cli[hf_xet]` (#15969)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Apr 3, 2025 at 00:37 UTC
55acf86bf817cca4baf9ed7a3f6e23be510d0198
2 files changed
+2
-2
requirements/common.txt
+1
-1
@@ -7,7 +7,7 @@ tqdm
7
blake3
8
py-cpuinfo
9
transformers >= 4.50.3
10
-huggingface-hub[hf-xet] >= 0.30.0 # Required for Xet downloads.
10
+huggingface-hub[hf_xet] >= 0.30.0 # Required for Xet downloads.
11
tokenizers >= 0.19.1 # Required for Llama 3.
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/test.in
+1
-1
@@ -31,7 +31,7 @@ opencv-python-headless >= 4.11.0 # required for video test
31
datamodel_code_generator # required for minicpm3 test
32
lm-eval[api]==0.4.8 # required for model evaluation test
33
transformers==4.50.3
34
-huggingface-hub[hf-xet]>=0.30.0 # Required for Xet downloads.
34
+huggingface-hub[hf_xet]>=0.30.0 # Required for Xet downloads.
35
# quantization
36
bitsandbytes>=0.45.3
37
buildkite-test-collector==0.1.9