| .. |
|
layers
|
d9b65e6c5f
feat: DeepSeek MoE support (#237)
|
hai 1 ano |
|
megatron
|
85c92acfb3
fix: do not initialize all-reduce at world_size=1
|
hai 1 ano |
|
models
|
d9b65e6c5f
feat: DeepSeek MoE support (#237)
|
hai 1 ano |
|
__init__.py
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
hai 1 ano |
|
hf_downloader.py
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
hai 1 ano |
|
loader.py
|
c0aac15421
feat: S-LoRA support (#222)
|
hai 1 ano |
|
metadata.py
|
31c95011a6
feat: FP8 E5M2 KV Cache (#226)
|
hai 1 ano |
|
sampling_metadata.py
|
1c46fa31ad
feat: add quadratic sampling (#233)
|
hai 1 ano |
|
utils.py
|
2755a48d51
merge dev branch into main (#153)
|
hai 1 ano |
AlpinDale
85c92acfb3
fix: do not initialize all-reduce at world_size=1