| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 年之前 |
|
api_server.py
|
a07fc83bc8
chore: proper util for aphrodite version
|
7 月之前 |
|
args.py
|
b8a19ba27f
chore: extend aphrodite metrics logging api
|
7 月之前 |
|
protocol.py
|
4f87a14998
chore: allow base64 embeddings
|
7 月之前 |
|
samplers.json
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
1 年之前 |
|
serving_chat.py
|
1d7f5c45b0
feat: add stream_options for chat completions
|
7 月之前 |
|
serving_completions.py
|
63b735bc2a
chore: optimize v2 block manager to match the performance of v1
|
7 月之前 |
|
serving_embedding.py
|
4f87a14998
chore: allow base64 embeddings
|
7 月之前 |
|
serving_engine.py
|
78de98463b
feat: return max_model_len in /v1/models
|
7 月之前 |
AlpinDale
63b735bc2a
chore: optimize v2 block manager to match the performance of v1