llama-stack/llama_stack/providers
Daniel Alvarez Sanchez b5a9ef4c6d
fix: Do not send an empty 'tools' list to remote vllm (#1957)
Fixes: #1955

Since 0.2.0, the vLLM gets an empty list (vs ``None``in 0.1.9 and
before) when there are no tools configured which causes the issue
described in #1955 p. This patch avoids sending the 'tools' param to the
vLLM altogether instead of an empty list.

It also adds a small unit test to avoid regressions.

The OpenAI
[specification](https://platform.openai.com/docs/api-reference/chat/create)
does not explicitly state that the list cannot be empty but I found this
out through experimentation and it might depend on the actual remote
vllm. In any case, as this parameter is Optional, is best to skip it
altogether if there's no tools configured.

Signed-off-by: Daniel Alvarez <dalvarez@redhat.com>
2025-04-15 20:31:12 -04:00
..
inline feat: Implement async job execution for torchtune training (#1437) 2025-04-14 08:59:11 -07:00
registry fix: use torchao 0.8.0 for inference (#1925) 2025-04-10 13:39:20 -07:00
remote fix: Do not send an empty 'tools' list to remote vllm (#1957) 2025-04-15 20:31:12 -04:00
tests refactor: move all llama code to models/llama out of meta reference (#1887) 2025-04-07 15:03:58 -07:00
utils feat: Implement async job execution for torchtune training (#1437) 2025-04-14 08:59:11 -07:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00
datatypes.py feat: add health to all providers through providers endpoint (#1418) 2025-04-14 11:59:36 +02:00