AlpinDale ee174ea4fd fix: guard for lora + chunked prefill il y a 7 mois
..
attention c8c6de64cd fix: typo in pallas backend il y a 7 mois
common ee174ea4fd fix: guard for lora + chunked prefill il y a 7 mois
distributed 44331a4d00 chore: improve p2p cache generation il y a 7 mois
endpoints a07fc83bc8 chore: proper util for aphrodite version il y a 7 mois
engine c482c09a3a fix: remove duplicated input processing in async engine il y a 7 mois
executor a89c9a0e92 fix: device ordinal issues with world_size and stuff il y a 7 mois
kv_quant e42a78381a feat: switch from pylint to ruff (#322) il y a 1 an
lora 42d2ee0f43 chore: better error logging for unsupported lora weights il y a 7 mois
modeling d0cca80b8b feat: support sharded tensorizer models il y a 7 mois
multimodal f2e94e2184 chore: minor llava cleanups in preparation for llava-next il y a 7 mois
processing f9a10145d1 fix: v2 block manager + prefix caching il y a 7 mois
quantization a33aaf3b42 chore: cleanup compressed tensors il y a 7 mois
spec_decode 4d1e613804 chore: minor simplifications il y a 7 mois
task_handler 34b41e0a87 chore: add coordinator to reduce code duplication in tp and pp il y a 7 mois
transformers_utils bba89fc6d3 chore: make the automatic rope scaling behave properly with rope_scaling arg, add rope theta il y a 7 mois
__init__.py a07fc83bc8 chore: proper util for aphrodite version il y a 7 mois
_custom_ops.py 7e54c3916d chore: factor out epilogues from cutlass kernels il y a 7 mois
py.typed 1c988a48b2 fix logging and add py.typed il y a 1 an
version.py 7e54c3916d chore: factor out epilogues from cutlass kernels il y a 7 mois