Skip to content
Projects

LoRAX Open-Source Contributions

4 PRs merged to predibase/lorax. Improved OpenAI-compatible serving interface, deterministic generation, streaming usage, and structured output support.

2024.03 — 2024.10 Open Source Contributor
Open Source LLM Serving Rust Python OpenAI API

Overview

Contributed 4 merged PRs to predibase/lorax, an open-source framework for serving fine-tuned LLMs. LoRAX is a production implementation of multi-LoRA serving research, and was used as the serving infrastructure for 310 fine-tuned models in the LoRA Land technical report. Each contribution addressed OpenAI API compatibility issues discovered during production operations.

Contributions

PR #358 — Chat Completion Stream Fix & API Improvements

  • Fixed chat completion final delta serialization for OpenAI client compatibility
  • Added /tokenize endpoint (token counting)
  • Improved Swagger/OpenAPI documentation

PR #374 — Seed Parameter Support

  • Added seed parameter to OpenAI-compatible endpoints
  • Enabled deterministic generation for reproducible testing and evaluation

PR #506 — Streaming Usage Information

  • Added token usage field to streaming chat completion responses
  • Aligned with OpenAI stream_options usage reporting behavior

PR #644 — Structured Output Support

  • Implemented response_format support (text, json_object, json_schema)
  • Reduced switching costs between OpenAI API and self-hosted LoRAX serving

Impact

These were not standalone OSS activities but direct solutions to serving interface issues discovered in production LLM deployments. PR #644’s structured output support in particular implements constrained decoding techniques at the serving interface level, and was directly applied to internal contract classification and checklist generation pipelines.

Open-source PR details

The cards below are rendered from the same component used in the Achievements page's open-source section.

Merged PRs

4 PRs

Contribution Period

2024.03 — 2024.10

Theme

OpenAI-compatible serving interface improvements

#358

Chat Completion Stream Fix & API Improvements

Fixed the last delta serialization in chat completion stream to match OpenAI client standards, added a /tokenize endpoint, and improved Swagger documentation.

RustStreamingOpenAI APIBug Fix
#374

Seed Parameter Support

Added seed parameter to OpenAI-compatible endpoints to enable deterministic generation.

RustDeterministicEvaluationFeature
#506

Streaming Usage Information

Added token usage information (prompt_tokens, completion_tokens, total_tokens) to streaming chat completion responses.

RustStreamingToken AccountingFeature
#644

Structured Output Support

Added support for text, json_object, and json_schema via the response_format parameter, strengthening compatibility with OpenAI's structured output interface.

RustStructured OutputJSON SchemaFeature