AlpinDale 6305e6f3f2 fix: no repeated IPC registration (#227) 1 éve
..
all_reduce 6305e6f3f2 fix: no repeated IPC registration (#227) 1 éve
attention 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
punica c0aac15421 feat: S-LoRA support (#222) 1 éve
quantization 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
activation_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 éve
cache.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
cache_kernels.cu 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
cuda_compat.h 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 éve
cuda_utils.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
cuda_utils_kernels.cu 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
dispatch_utils.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
layernorm_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 éve
ops.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
pos_encoding_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 éve
pybind.cpp 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 éve
reduction.cuh 2755a48d51 merge dev branch into main (#153) 1 éve