CUDA: add FP32 FlashAttention vector kernel (llama/7188)

ggml : remove oboslete alibi code (skipme) (#0)

ggml : full ALiBi support (llama/7192)

CUDA: generalize FP16 fattn vec kernel (llama/7061)

Introduction of CUDA Graphs to LLama.cpp (llama/6766)

CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (llama/7019)

ggml : add Flash Attention (llama/5021)

Fix more int overflow during quant (PPL/CUDA). (llama/6563)

ggml : group all experts in a single ggml_mul_mat_id (llama/6505)

feat: implemented sigmoid function (ggml/806)

llama : add Command R Plus support (llama/6491)

sync : llama.cpp (skip)

ggml : mul_mat_id use the same tensor for all the experts (llama/6387)

sync : ggml (#2001)