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, 08:30 UTC
[Bugfix]: handle hf-xet CAS error when loading Qwen3 weights in vLLM (#18701)
dylan committed
May 26, 2025 at 22:10 UTC
243eb9199fa5962e8edf46e47170f68b3f6a0116
1 file changed
+1
-1
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] >= 0.30.0 # Required for Xet downloads.
11
+huggingface-hub[hf_xet] >= 0.32.0 # 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.