.. |
rpc
|
77c4fbd5c9
fix: better async request cancellation (#641)
|
há 4 meses atrás |
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
há 1 ano atrás |
api_server.py
|
59264d32e9
fix: hardcoded float16 in embedding mode check (#645)
|
há 4 meses atrás |
args.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
logits_processors.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
protocol.py
|
48f7216c49
add to procotol
|
há 4 meses atrás |
run_batch.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
samplers.json
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
há 11 meses atrás |
serving_chat.py
|
3648170750
fix: gracefully handle missing chat template (#642)
|
há 4 meses atrás |
serving_completions.py
|
77c4fbd5c9
fix: better async request cancellation (#641)
|
há 4 meses atrás |
serving_embedding.py
|
77c4fbd5c9
fix: better async request cancellation (#641)
|
há 4 meses atrás |
serving_engine.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 5 meses atrás |
serving_tokenization.py
|
3648170750
fix: gracefully handle missing chat template (#642)
|
há 4 meses atrás |