ylying fe3be1595d Add qwen2 tie word embedding (#630)

2024-07-16 11:48:49 -07:00

..

constrained

Format (#593)

2024-07-05 10:06:17 -07:00

layers

Fix memory pool index error (#616)

2024-07-13 16:45:11 -07:00

managers

Fix flush cache (#627)

2024-07-15 20:44:04 -07:00

models

Add qwen2 tie word embedding (#630)

2024-07-16 11:48:49 -07:00

conversation.py

Higher priority for user input of max_prefill_tokens & format (#540)

2024-06-12 21:48:40 -07:00

flush_cache.py

Improve doc strings (#518)

2024-06-08 02:39:32 -07:00

hf_transformers_utils.py

Format (#593)

2024-07-05 10:06:17 -07:00

memory_pool.py

Fix flush cache (#627)

2024-07-15 20:44:04 -07:00

mm_utils.py

Handle grayscale images in expand2square (#97)

2024-01-24 16:23:11 -08:00

model_config.py

Fix Llava model (#594)

2024-07-06 00:58:46 -07:00

openai_api_adapter.py

Fix streaming (#600)

2024-07-07 01:55:58 -07:00

openai_protocol.py

Fix the default argument of OpenAI Chat completion (#605)

2024-07-09 02:04:43 -07:00

sampling_params.py

SamplingParams add "spaces_between_special_tokens" argument (#392)

2024-04-30 16:17:12 -07:00

server_args.py

Improve tensor parallel performance (#625)

2024-07-15 07:10:51 -07:00

server.py

Disable NCCL_NVLS by default (#631)

2024-07-16 09:05:10 -07:00

utils.py

Optimize mem indices mangement (#619)

2024-07-13 23:39:37 -07:00