AlpinDale 53d0ba7c7c api: add endpoint for loading and unloading the model (#926) 3 maanden geleden
..
adapter_commons 2f61644f6e SPMD optimizations (#824) 4 maanden geleden
assets 653d1a08d4 feat: add support for audio models (#891) 3 maanden geleden
attention f7f3fed265 feat: add async postprocessor (#925) 3 maanden geleden
common f7f3fed265 feat: add async postprocessor (#925) 3 maanden geleden
distributed 2940da2c7b distributed: fix custom allreduce p2p cache file generation (#922) 3 maanden geleden
endpoints 53d0ba7c7c api: add endpoint for loading and unloading the model (#926) 3 maanden geleden
engine f7f3fed265 feat: add async postprocessor (#925) 3 maanden geleden
executor 0c6d90dade neuron: add support for tensor parallelism (#923) 3 maanden geleden
inputs 908ff753a1 fix: phi_3.5_v loading (#896) 3 maanden geleden
kv_quant 8a71788372 Add OLMoE (#772) 5 maanden geleden
lora 369600855a xpu: disable punica kernels for XPU (#864) 3 maanden geleden
modeling 5cb2e998d8 quants: update compressed tensors lifecycle to remove `prefix` from `create_weights` (#924) 3 maanden geleden
multimodal 653d1a08d4 feat: add support for audio models (#891) 3 maanden geleden
platforms 81c28d2a7f fix: use nvml to get consistent device names (#739) 6 maanden geleden
plugins 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) 3 maanden geleden
processing f7f3fed265 feat: add async postprocessor (#925) 3 maanden geleden
prompt_adapter 2f61644f6e SPMD optimizations (#824) 4 maanden geleden
quantization f7f3fed265 feat: add async postprocessor (#925) 3 maanden geleden
server 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) 3 maanden geleden
spec_decode 3b684a8a54 spec decode: streamline batch expansion tensor manipulation (#918) 3 maanden geleden
task_handler f7f3fed265 feat: add async postprocessor (#925) 3 maanden geleden
transformers_utils 132aa2abe4 spec decode: add support for EAGLE (#899) 3 maanden geleden
triton_utils f1d0b77c92 [0.6.0] Release Candidate (#481) 6 maanden geleden
__init__.py f1d0b77c92 [0.6.0] Release Candidate (#481) 6 maanden geleden
_core_ext.py 9296d4b25d feat: dynamo support for ScalarType (#733) 6 maanden geleden
_custom_ops.py 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 3 maanden geleden
_ipex_ops.py f1d0b77c92 [0.6.0] Release Candidate (#481) 6 maanden geleden
connections.py c6c91edab7 ci: update & overhaul test units (#769) 4 maanden geleden
constants.py 2f61644f6e SPMD optimizations (#824) 4 maanden geleden
py.typed 1c988a48b2 fix logging and add py.typed 1 jaar geleden
scalar_type.py f1d0b77c92 [0.6.0] Release Candidate (#481) 6 maanden geleden
version.py 8b8d2ce7e2 ci: bump aphrodite version to 0.6.4.post1 (#859) 3 maanden geleden