mirror of
https://github.com/NousResearch/atropos.git
synced 2026-04-19 12:57:58 +00:00
Add dummy openai managed server
This commit is contained in:
parent
462abbebf7
commit
10f651289c
4 changed files with 235 additions and 11 deletions
|
|
@ -2,6 +2,12 @@
|
|||
|
||||
This module provides server abstraction layers for different LLM inference backends.
|
||||
|
||||
## ManagedServer
|
||||
|
||||
For automatic token and logprob tracking, see the [ManagedServer Guide](MANAGED_SERVER.md).
|
||||
|
||||
> **Note:** OpenAI endpoints do not support token IDs/logprobs required for ManagedServer. Set `ATROPOS_ALLOW_DUMMY_MANAGED_SERVER=1` to use a placeholder implementation for testing/evaluation. See [OpenAI Endpoint Limitations](MANAGED_SERVER.md#openai-endpoint-limitations) for details.
|
||||
|
||||
## Reasoning Model Support
|
||||
|
||||
The `ReasoningConfig` class enables support for reasoning/thinking models across different providers.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue