What an engine downloads by a Hugging Face id is asked about too
CI / test (push) Failing after 8m0s

From review. An adapter given by its id is downloaded by vLLM itself, and
a TensorRT-LLM model by its id by TensorRT-LLM, past the node's check and
not held to safetensors: a model with either is refused when it is added,
unless it says allow_pickle, with how to mirror its safetensors instead.
vLLM's own model by id stays allowed: the agent gives it --load-format
safetensors. A test holds every preset to its own pickle check.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-29 11:06:11 +01:00
1 parent 5eac62d556
commit 258591b3f2
3 files changed
+83 -2

No files matched your search

+4 -2
View File
@@ -892,8 +892,10 @@ files were checked, can say so:
```
A local path is judged by its name as any source is; a local directory is
not looked into, nor a model an engine downloads itself other than by its
Hugging Face id (an adapter by id, TensorRT-LLM's checkpoints).
not looked into. What an engine downloads itself by a Hugging Face id, past
the node — an adapter given by its id, a TensorRT-LLM model's — is refused
when the model is added, unless it says `allow_pickle`: mirror its
safetensors and give that instead.
Put them where the node can read them. `scp`, a shared filesystem, or the
engine's own downloader are all valid, and which you want depends on how many