| .. |
|
__init__.py
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
il y a 5 mois |
|
loader.py
|
349a612338
chore: bump bitsandbytes version to latest; enable cuda graphs for 4bit bnb (#1123)
|
il y a 1 mois |
|
neuron.py
|
145e554a4d
neuron: add 8bit quantization for Neuron (#994)
|
il y a 2 mois |
|
openvino.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
il y a 2 mois |
|
tensorizer.py
|
5b03d67abb
Core: add output streaming support to multi-step + async (#1112)
|
il y a 1 mois |
|
utils.py
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
il y a 2 mois |
|
weight_utils.py
|
3e6addcc2c
LLM: enable batched inference for llm.chat() API (#1120)
|
il y a 1 mois |
AlpinDale
349a612338
chore: bump bitsandbytes version to latest; enable cuda graphs for 4bit bnb (#1123)