| .. |
|
e2e
|
0859dc3bc0
tests: refactor speculative decoding tests to remove the async engine (#1021)
|
há 1 semana atrás |
|
__init__.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
há 1 mês atrás |
|
test_batch_expansion.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
há 1 mês atrás |
|
test_dynamic_spec_decode.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
há 1 mês atrás |
|
test_metrics.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
há 1 mês atrás |
|
test_multi_step_worker.py
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
há 2 semanas atrás |
|
test_ngram_worker.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
há 1 mês atrás |
|
test_spec_decode_worker.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
há 2 semanas atrás |
|
test_utils.py
|
564d197687
spec decode: match the original rank computation impl for spec decoding (#954)
|
há 2 semanas atrás |
|
utils.py
|
1fac86c325
core: factor out common code in SequenceData (#1083)
|
há 8 horas atrás |
AlpinDale
1fac86c325
core: factor out common code in SequenceData (#1083)