34fcc5a4ac
* First attempt * No permute during convert (fixes qk tensors), proper norm application. * RoPE = NeoX * Coherence! * Migrate xielu params from tensors to hyperparameters * Simple CUDA kernel * Revert stupid LLM refactorings * Chat template support * configchecker / flake8 errors * Reorder unary.cu * I do conclude that LLMs are, in fact, stupid. * Fix after merge * Final newline * Make xIELU an UNARY_OP * Final newline * Correctly account for parameter shift * Argh. * Update ggml/src/ggml-cpu/unary-ops.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Refactor: remove unused methods, inline and factorize softplus, add const modifiers * Revert CUDA changes, implement xIELU as a separate OP * Pesky newline * Add float2half / half2float for F16 inputs/outputs * CUDA variants, attempt 2 * Actually, attempt 3 * Update ggml/src/ggml-cuda/unary.cu Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * Missing convert header * Proper formula and reference for xIELU in the comments. * Modify unary-ops.cpp to add the functor-based logic besides the template system to retain optimizations * Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Add tensor mappings for Apertus to global list instead * Fix lazy on scalars * Update ggml/src/ggml-cuda/unary.cu Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * Add comment about the constraints on positive/negative alpha * Change `softplus` to `ggml_softplus` --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Johannes Gäßler <johannesg@5d6.de> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
78 lines
2.8 KiB
Plaintext
78 lines
2.8 KiB
Plaintext
#include "common.cuh"
|
|
|
|
#define CUDA_NEG_BLOCK_SIZE 256
|
|
#define CUDA_STEP_BLOCK_SIZE 256
|
|
#define CUDA_GELU_BLOCK_SIZE 256
|
|
#define CUDA_SILU_BLOCK_SIZE 256
|
|
#define CUDA_SILU_BACK_BLOCK_SIZE 256
|
|
#define CUDA_TANH_BLOCK_SIZE 256
|
|
#define CUDA_RELU_BLOCK_SIZE 256
|
|
#define CUDA_SIGMOID_BLOCK_SIZE 256
|
|
#define CUDA_HARDSIGMOID_BLOCK_SIZE 256
|
|
#define CUDA_EXP_BLOCK_SIZE 256
|
|
#define CUDA_HARDSWISH_BLOCK_SIZE 256
|
|
#define CUDA_SQR_BLOCK_SIZE 256
|
|
#define CUDA_SQRT_BLOCK_SIZE 256
|
|
#define CUDA_SIN_BLOCK_SIZE 256
|
|
#define CUDA_COS_BLOCK_SIZE 256
|
|
#define CUDA_GLU_BLOCK_SIZE 256
|
|
#define CUDA_XIELU_BLOCK_SIZE 256
|
|
|
|
void ggml_cuda_op_abs(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_sgn(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_neg(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_step(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_gelu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_silu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_silu_back(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_gelu_erf(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_gelu_quick(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_tanh(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_sigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_hardsigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_exp(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_hardswish(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_leaky_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_sqr(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_sqrt(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_sin(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_cos(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_log(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_elu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_reglu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_geglu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_swiglu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_swiglu_oai(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_geglu_erf(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_geglu_quick(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_xielu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|