AlpinDale b47a39026d feat: introduce MQAphroditeEngine 1 mês atrás
..
__init__.py 07aa2a492f upstream: add option to specify tokenizer 1 ano atrás
block.py 7df7b8ca53 optimization: reduce end-to-end overhead from python obj allocation (#666) 4 meses atrás
config.py b3f9ab3b72 quant: add tensor parallel support for bitsandbytes (#1052) 1 mês atrás
connections.py f1d0b77c92 [0.6.0] Release Candidate (#481) 5 meses atrás
envs.py b47a39026d feat: introduce MQAphroditeEngine 1 mês atrás
grammar.py 8a71788372 Add OLMoE (#772) 3 meses atrás
logger.py 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) 1 mês atrás
logits_processor.py 8a71788372 Add OLMoE (#772) 3 meses atrás
outputs.py 055c8905a3 api: add sampling/engine option to return only deltas or final output (#1035) 1 mês atrás
pooling_params.py 2f61644f6e SPMD optimizations (#824) 2 meses atrás
sampling_params.py 055c8905a3 api: add sampling/engine option to return only deltas or final output (#1035) 1 mês atrás
sequence.py 055c8905a3 api: add sampling/engine option to return only deltas or final output (#1035) 1 mês atrás
test_utils.py 8a71788372 Add OLMoE (#772) 3 meses atrás
utils.py 9bdf8d5bfa mamba: enable continuous batching for mamba kernels (#1055) 1 mês atrás