| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
il y a 1 an |
|
api_server.py
|
fe431bb840
check for next port if current is unavailable
|
il y a 6 mois |
|
args.py
|
8f9cb7235c
chore: allow multiple served model names
|
il y a 8 mois |
|
protocol.py
|
be8154a8a0
feat: proper embeddings API with e5-mistral-7b support
|
il y a 6 mois |
|
samplers.json
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
il y a 11 mois |
|
serving_chat.py
|
e8b7f53321
allow prompt token IDs in the logits processor api
|
il y a 6 mois |
|
serving_completions.py
|
be8154a8a0
feat: proper embeddings API with e5-mistral-7b support
|
il y a 6 mois |
|
serving_embedding.py
|
54a4cef647
add bias and tie word embedding support for llama
|
il y a 6 mois |
|
serving_engine.py
|
696f2cd59c
add phi3_small support with blocksparse attention
|
il y a 6 mois |
AlpinDale
696f2cd59c
add phi3_small support with blocksparse attention