oobabooga 521ddbb722 Security: restrict API model loading args to UI-exposed parameters ... The /v1/internal/model/load endpoint previously allowed setting any shared.args attribute, including security-sensitive flags like trust_remote_code. Now only keys from list_model_elements() are accepted.		2026-03-06 01:57:02 -03:00
..
cache_embedding_model.py	Make /v1/embeddings functional, add request/response types	2023-11-10 07:34:27 -08:00
completions.py	API: Fix function calling for Qwen, Mistral, GPT-OSS, and other models	2026-03-06 00:55:33 -03:00
embeddings.py	Openai embedding fix to support jina-embeddings-v2 (#4642)	2023-11-18 20:24:29 -03:00
errors.py	extensions/openai: Fixes for: embeddings, tokens, better errors. +Docs update, +Images, +logit_bias/logprobs, +more. (#3122)	2023-07-24 11:28:12 -03:00
images.py	Image: Several fixes	2025-12-05 05:58:57 -08:00
logits.py	New llama.cpp loader (#6846)	2025-04-18 09:59:37 -03:00
models.py	Security: restrict API model loading args to UI-exposed parameters	2026-03-06 01:57:02 -03:00
moderations.py	Lint	2023-11-16 18:03:06 -08:00
script.py	API: Add parallel request support for llama.cpp and ExLlamaV3	2026-03-05 16:49:58 -08:00
tokens.py	Add types to the encode/decode/token-count endpoints	2023-11-07 19:32:14 -08:00
typing.py	API: Add command-line flags to override default generation parameters	2026-03-06 01:36:45 -03:00
utils.py	API: Fix function calling for Qwen, Mistral, GPT-OSS, and other models	2026-03-06 00:55:33 -03:00