Morph MORPH
SIGN IN SIGN UP
hpcaitech / ColossalAI UNCLAIMED

Making large AI models cheaper, faster and more accessible

0 0 38 Python

COMMITS

/ extensions/csrc/kernel/cuda/context_kv_cache_memcpy_kernel.cu
main
April 30, 2024
傅
[Inference/Feat] Add kvcache quant support for fused_rotary_embedding_cache_copy (#5680)
傅剑寒 committed
ef8e4ff
S
[Inference/Kernel] refactor kvcache manager and rotary_embedding and kvcache_memcpy oper… (#5663)
Steve Luo committed
5cd75ce
傅
[Inference/Feat] Feat quant kvcache step2 (#5674)
傅剑寒 committed
808ee6e
April 26, 2024
傅
[Inference/Feat] Add kvcache quantization support for FlashDecoding (#5656)
傅剑寒 committed
8ccb671
April 24, 2024
傅
[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613)
傅剑寒 committed
279300d