Ying Sheng b68c4c073b fix: force max new tokens to be 1 for embedding request (#1019)

2024-08-10 13:46:42 -07:00

..

models

fix: force max new tokens to be 1 for embedding request (#1019)

2024-08-10 13:46:42 -07:00

sampling/penaltylib

bugfix: penalizers to be merged before reqs (#1001)

2024-08-09 21:46:24 +10:00

run_suite.py

Add openai embedding API (#997)

2024-08-09 11:19:18 -07:00

test_chunked_prefill.py

chore: update vllm to 0.5.4 (#966)

2024-08-07 21:15:41 +10:00

test_embedding_openai_server.py

Support embedding input as a list (#1014)

2024-08-10 08:39:05 -07:00

test_eval_accuracy.py

chore: update vllm to 0.5.4 (#966)

2024-08-07 21:15:41 +10:00

test_models_from_modelscope.py

support models from www.modelscope.cn (#994)

2024-08-09 02:52:14 -07:00

test_openai_server.py

support more optioin about usage in stream mode (#985)

2024-08-08 09:41:57 +00:00

test_skip_tokenizer_srt.py

Add skip_tokenizer_init args. (#959)

2024-08-09 12:14:13 -07:00

test_srt_endpoint.py

chore: update vllm to 0.5.4 (#966)

2024-08-07 21:15:41 +10:00

test_torch_compile.py

chore: update vllm to 0.5.4 (#966)

2024-08-07 21:15:41 +10:00

test_vision_openai_server.py

chore: update vllm to 0.5.4 (#966)

2024-08-07 21:15:41 +10:00