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>
30 lines
1.8 KiB
C
30 lines
1.8 KiB
C
#pragma once
|
|
|
|
#include "common.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
void ggml_compute_forward_abs(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_sgn(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_neg(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_step(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_tanh(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_elu(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_relu(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_sigmoid(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_hardsigmoid(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_exp(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_hardswish(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_sqr(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_sqrt(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_sin(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_cos(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_log(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
void ggml_compute_forward_xielu(const struct ggml_compute_params * params, struct ggml_tensor * dst);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|