takatost 9ae91a2ec3 feat: optimize xinference request max token key and stop reason (#998) 3 vuotta sitten
..
__init__.py 5fa2161b05 feat: server multi models support (#799) 3 vuotta sitten
azure_chat_open_ai.py 5fa2161b05 feat: server multi models support (#799) 3 vuotta sitten
azure_open_ai.py 5fa2161b05 feat: server multi models support (#799) 3 vuotta sitten
chat_open_ai.py 5fa2161b05 feat: server multi models support (#799) 3 vuotta sitten
fake.py 5fa2161b05 feat: server multi models support (#799) 3 vuotta sitten
huggingface_endpoint_llm.py a76fde3d23 feat: optimize hf inference endpoint (#975) 3 vuotta sitten
open_ai.py 5fa2161b05 feat: server multi models support (#799) 3 vuotta sitten
openllm.py 866ee5da91 fix: openllm generate cutoff (#945) 3 vuotta sitten
replicate_llm.py 5fa2161b05 feat: server multi models support (#799) 3 vuotta sitten
spark.py f42e7d1a61 feat: add spark v2 support (#885) 3 vuotta sitten
tongyi_llm.py 5fa2161b05 feat: server multi models support (#799) 3 vuotta sitten
wenxin.py c4d759dfba fix: wenxin error not raise when stream mode (#884) 3 vuotta sitten
xinference_llm.py 9ae91a2ec3 feat: optimize xinference request max token key and stop reason (#998) 3 vuotta sitten