Skip to content

Endpoint failed to start due to ShardFailed on hugging face inference endpoint #3317

@relativity-codes

Description

@relativity-codes

System Info

When starting the endpoint, the server crashes with ShardFailed. The backend process exits with code 1 before serving requests.

[Server message]Endpoint failed to start
Exit code: 1. Reason: :"backends/v3/src/client/mod.rs","line_number":45,"span":{"batch_id":"Some(69)","name":"clear_cache"},"spans":[{"batch_size":1,"name":"batch"},{"name":"prefill"},{"batch_id":"Some(69)","name":"clear_cache"},{"batch_id":"Some(69)","name":"clear_cache"}]}
{"timestamp":"2025-08-29T14:40:17.288163Z","level":"ERROR","message":"Request failed during generation: Server error: error trying to connect: No such file or directory (os error 2)","target":"text_generation_router_v3::backend","filename":"backends/v3/src/backend.rs","line_number":546,"span":{"name":"send_error"},"spans":[{"parameters":"GenerateParameters { best_of: None, temperature: None, repetition_penalty: None, frequency_penalty: None, top_k: None, top_p: None, typical_p: None, do_sample: true, max_new_tokens: Some(4800), return_full_text: None, stop: [], truncate: None, watermark: false, details: true, decoder_input_details: false, seed: None, top_n_tokens: None, grammar: None, adapter_id: None }","name":"chat_completions"},{"name":"generate"},{"name":"generate_stream"},{"name":"schedule"},{"name":"infer"},{"name":"send_error"}]}
{"timestamp":"2025-08-29T14:40:17.300833Z","level":"ERROR","fields":{"message":"Shard 0 crashed"},"target":"text_generation_launcher"}
{"timestamp":"2025-08-29T14:40:17.300875Z","level":"INFO","fields":{"message":"Terminating webserver"},"target":"text_generation_launcher"}
{"timestamp":"2025-08-29T14:40:17.300901Z","level":"INFO","fields":{"message":"Waiting for webserver to gracefully shutdown"},"target":"text_generation_launcher"}
{"timestamp":"2025-08-29T14:40:17.301003Z","level":"INFO","message":"signal received, starting graceful shutdown","target":"text_generation_router::server","filename":"router/src/server.rs","line_number":2395}
{"timestamp":"2025-08-29T14:40:17.501249Z","level":"INFO","fields":{"message":"webserver terminated"},"target":"text_generation_launcher"}
{"timestamp":"2025-08-29T14:40:17.501293Z","level":"INFO","fields":{"message":"Shutting down shards"},"target":"text_generation_launcher"}
Error: ShardFailed

Information

  • Docker
  • The CLI directly

Tasks

  • An officially supported command
  • My own modifications

Reproduction

happens on hugging face inference endpoint

Expected behavior

this related to deprecation of a dependency

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions