AlpinDale 05e45aeb53 fix: dtype mismatch for paligemma il y a 6 mois
..
adapter_commons 99680b2d23 feat: soft prompts (#589) il y a 6 mois
attention a2d476183f fix: remove scipy and re-implement CSR matrix il y a 6 mois
common ddb28a80a3 fix: bump torch for rocm, unify CUDA_VISIBLE_DEVICES for cuda and rocm il y a 6 mois
distributed cc6399792f fix: keep consistent with how pytorch finds libcudart.so il y a 6 mois
endpoints a3b56353fa fix: another one missed il y a 6 mois
engine 63becc67c0 fix: prompt logprob detokenization il y a 6 mois
executor 4501ae5f15 fix: neuron executor for adapters il y a 6 mois
inputs 4f7d212b70 feat: remove vision language config il y a 6 mois
kv_quant e42a78381a feat: switch from pylint to ruff (#322) il y a 1 an
lora 99680b2d23 feat: soft prompts (#589) il y a 6 mois
modeling 05e45aeb53 fix: dtype mismatch for paligemma il y a 6 mois
multimodal c11a8bdaad fix: calculate max number of multi-modal tokens automatically il y a 6 mois
platforms 1a40bf438b fix: incorrect gpu capability when used mixed gpus il y a 6 mois
processing 99680b2d23 feat: soft prompts (#589) il y a 6 mois
prompt_adapter 99680b2d23 feat: soft prompts (#589) il y a 6 mois
quantization 500f3b654f fix: support bias term in compressed-tensors quant il y a 6 mois
spec_decode 16dff9babc chore: enable bonus token in spec decoding for KV cache based models il y a 6 mois
task_handler ddb28a80a3 fix: bump torch for rocm, unify CUDA_VISIBLE_DEVICES for cuda and rocm il y a 6 mois
transformers_utils 63becc67c0 fix: prompt logprob detokenization il y a 6 mois
__init__.py a07fc83bc8 chore: proper util for aphrodite version il y a 7 mois
_custom_ops.py ad24e74a99 feat: FP8 weight-only quantization support for Ampere GPUs il y a 6 mois
_ipex_ops.py 6a57861fca feat: initial XPU support via intel_extension_for_pytorch (#571) 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