mirror of
https://github.com/discourse/discourse.git
synced 2026-08-08 17:53:55 +08:00
c9145ca98cSelect the dedicated vLLM dialect before the OpenAI-compatible fallback. Preserve response IDs on tool calls so parallel calls share provider batch metadata, and account for vLLM's top-level prompt cache token fields. --------- Co-authored-by: discourse-patch-triage[bot] <272280883+discourse-patch-triage[bot]@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| chat_gpt.rb | ||
| claude.rb | ||
| claude_tools.rb | ||
| cohere_tools.rb | ||
| command.rb | ||
| converse.rb | ||
| converse_tools.rb | ||
| dialect.rb | ||
| fake.rb | ||
| gemini.rb | ||
| mistral.rb | ||
| nova.rb | ||
| nova_tools.rb | ||
| ollama.rb | ||
| ollama_tools.rb | ||
| open_ai_compatible.rb | ||
| open_ai_responses.rb | ||
| open_ai_tools.rb | ||
| vllm.rb | ||
| xml_tools.rb | ||
