AlpinDale b3f9ab3b72 quant: add tensor parallel support for bitsandbytes (#1052) пре 1 месец
..
__init__.py 89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745) пре 4 месеци
loader.py b3f9ab3b72 quant: add tensor parallel support for bitsandbytes (#1052) пре 1 месец
neuron.py 145e554a4d neuron: add 8bit quantization for Neuron (#994) пре 1 месец
openvino.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) пре 1 месец
tensorizer.py 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) пре 1 месец
utils.py 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934) пре 1 месец
weight_utils.py dcb36de9c4 quants: add support for NVIDIA's ModelOpt checkpoints (#1013) пре 1 месец