AlpinDale 5d288aa76c feat: add fast hadamard transformation kernels (#232) 1 jaar geleden
..
all_reduce 6305e6f3f2 fix: no repeated IPC registration (#227) 1 jaar geleden
attention 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 jaar geleden
hadamard 5d288aa76c feat: add fast hadamard transformation kernels (#232) 1 jaar geleden
punica c0aac15421 feat: S-LoRA support (#222) 1 jaar geleden
quantization c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 1 jaar geleden
activation_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 jaar geleden
cache.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 jaar geleden
cache_kernels.cu 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 jaar geleden
cuda_compat.h 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 jaar geleden
cuda_utils.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 jaar geleden
cuda_utils_kernels.cu 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 jaar geleden
dispatch_utils.h 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 jaar geleden
layernorm_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 jaar geleden
ops.h c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 1 jaar geleden
pos_encoding_kernels.cu 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 jaar geleden
pybind.cpp c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 1 jaar geleden
reduction.cuh 2755a48d51 merge dev branch into main (#153) 1 jaar geleden