-
Notifications
You must be signed in to change notification settings - Fork 289
Description
System Info
While trying to run any model with turing-1.5 version of docker image of TEI, no model couldn't be downloaded with T4 GPU
Attaching error logs from the Console:
docker run --gpus '"device=1"' -p 9050:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:turing-1.5 --model-id $model
turing-1.5: Pulling from huggingface/text-embeddings-inference
Digest: sha256:67cbbfae52d8d07c672ce7cab0d437f84127ce5f0f21721011851c43b4def642
Status: Image is up to date for ghcr.io/huggingface/text-embeddings-inference:turing-1.5
2025-07-03T11:09:40.340399Z INFO text_embeddings_router: router/src/main.rs:175: Args { model_id: "BAA*/-*****-**rge", revision: None, tokenization_workers: None, dtype: None, pooling: None, max_concurrent_requests: 512, max_batch_tokens: 16384, max_batch_requests: None, max_client_batch_size: 32, auto_truncate: false, default_prompt_name: None, default_prompt: None, hf_api_token: None, hostname: "ae0ce12ade1f", port: 80, uds_path: "/tmp/text-embeddings-inference-server", huggingface_hub_cache: Some("/data"), payload_limit: 2000000, api_key: None, json_output: false, otlp_endpoint: None, otlp_service_name: "text-embeddings-inference.server", cors_allow_origin: None }
2025-07-03T11:09:40.340555Z INFO hf_hub: /root/.cargo/registry/src/index.crates.io-6f17d22bba15001f/hf-hub-0.3.2/src/lib.rs:55: Token file not found "/root/.cache/huggingface/token"
2025-07-03T11:09:40.482154Z INFO download_pool_config: text_embeddings_core::download: core/src/download.rs:38: Downloading 1_Pooling/config.json
2025-07-03T11:09:45.982195Z INFO download_new_st_config: text_embeddings_core::download: core/src/download.rs:62: Downloading config_sentence_transformers.json
2025-07-03T11:09:46.110960Z INFO download_artifacts: text_embeddings_core::download: core/src/download.rs:21: Starting download
2025-07-03T11:09:46.110978Z INFO download_artifacts: text_embeddings_core::download: core/src/download.rs:23: Downloading config.json
Error: Could not download model artifacts
Caused by:
0: request error: builder error: relative URL without a base
1: builder error: relative URL without a base
2: relative URL without a base
However, same command will work with turing-1.7 version.
Information
- Docker
- The CLI directly
Tasks
- An officially supported command
- My own modifications
Reproduction
Use turing-1.5 TEI image on T4 GPU.
Choose any model to load
Expected behavior
Working with turing-1.5 version on T4 GPU