AlpinDale c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) il y a 1 an
..
all_reduce 6305e6f3f2 fix: no repeated IPC registration (#227) il y a 1 an
attention 31c95011a6 feat: FP8 E5M2 KV Cache (#226) il y a 1 an
punica c0aac15421 feat: S-LoRA support (#222) il y a 1 an
quantization c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) il y a 1 an
activation_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) il y a 1 an
cache.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) il y a 1 an
cache_kernels.cu 31c95011a6 feat: FP8 E5M2 KV Cache (#226) il y a 1 an
cuda_compat.h 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) il y a 1 an
cuda_utils.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) il y a 1 an
cuda_utils_kernels.cu 31c95011a6 feat: FP8 E5M2 KV Cache (#226) il y a 1 an
dispatch_utils.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) il y a 1 an
layernorm_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) il y a 1 an
ops.h c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) il y a 1 an
pos_encoding_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) il y a 1 an
pybind.cpp c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) il y a 1 an
reduction.cuh 2755a48d51 merge dev branch into main (#153) il y a 1 an