AlpinDale 05e45aeb53 fix: dtype mismatch for paligemma 6 months ago
..
adapter_commons 99680b2d23 feat: soft prompts (#589) 6 months ago
attention a2d476183f fix: remove scipy and re-implement CSR matrix 6 months ago
common ddb28a80a3 fix: bump torch for rocm, unify CUDA_VISIBLE_DEVICES for cuda and rocm 6 months ago
distributed cc6399792f fix: keep consistent with how pytorch finds libcudart.so 6 months ago
endpoints a3b56353fa fix: another one missed 6 months ago
engine 63becc67c0 fix: prompt logprob detokenization 6 months ago
executor 4501ae5f15 fix: neuron executor for adapters 6 months ago
inputs 4f7d212b70 feat: remove vision language config 6 months ago
kv_quant e42a78381a feat: switch from pylint to ruff (#322) 1 year ago
lora 99680b2d23 feat: soft prompts (#589) 6 months ago
modeling 05e45aeb53 fix: dtype mismatch for paligemma 6 months ago
multimodal c11a8bdaad fix: calculate max number of multi-modal tokens automatically 6 months ago
platforms 1a40bf438b fix: incorrect gpu capability when used mixed gpus 6 months ago
processing 99680b2d23 feat: soft prompts (#589) 6 months ago
prompt_adapter 99680b2d23 feat: soft prompts (#589) 6 months ago
quantization 500f3b654f fix: support bias term in compressed-tensors quant 6 months ago
spec_decode 16dff9babc chore: enable bonus token in spec decoding for KV cache based models 6 months ago
task_handler ddb28a80a3 fix: bump torch for rocm, unify CUDA_VISIBLE_DEVICES for cuda and rocm 6 months ago
transformers_utils 63becc67c0 fix: prompt logprob detokenization 6 months ago
__init__.py a07fc83bc8 chore: proper util for aphrodite version 7 months ago
_custom_ops.py ad24e74a99 feat: FP8 weight-only quantization support for Ampere GPUs 6 months ago
_ipex_ops.py 6a57861fca feat: initial XPU support via intel_extension_for_pytorch (#571) 7 months ago
py.typed 1c988a48b2 fix logging and add py.typed 1 year ago
version.py 7e54c3916d chore: factor out epilogues from cutlass kernels 7 months ago