| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 rok temu |
|
block.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
4 miesięcy temu |
|
config.py
|
73177656ed
feat: quant_llm support (#755)
|
4 miesięcy temu |
|
connections.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
|
grammar.py
|
0527131e93
fix: grammar logits processor (#268)
|
11 miesięcy temu |
|
logger.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
|
logits_processor.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 miesięcy temu |
|
outputs.py
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
4 miesięcy temu |
|
pooling_params.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
|
sampling_params.py
|
ad181e3fef
feat: bring back dynatemp (#754)
|
4 miesięcy temu |
|
sequence.py
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
4 miesięcy temu |
|
test_utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 miesięcy temu |
|
utils.py
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
4 miesięcy temu |
AlpinDale
73177656ed
feat: quant_llm support (#755)