mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
fd1234cb46
* oai moe * compat with new checkpoint * add attn sink impl * add rope scaling yarn * logits match with latest transformers code * wip chat template * rm trailing space * use ggml_scale_bias * rm redundant is_swa_all * convert interleaved gate_up * graph : fix activation function to match reference (#7) * vocab : handle o200k_harmony special tokens * ggml : add attention sinks support (#1) * llama : add attn sinks * ggml : add attn sinks * cuda : add attn sinks * vulkan : add support for sinks in softmax remove unnecessary return * ggml : add fused swiglu_oai op (#11) * ggml : add fused swiglu_oai op * Update ggml/src/ggml-cpu/ops.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * update CUDA impl * cont : metal impl * add vulkan impl * test-backend-ops : more test cases, clean up * llama : remove unfused impl * remove extra lines --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: slaren <slarengh@gmail.com> * repack mxfp4 upon conversion * clean up a bit * enable thinking * add quick hack to render only some special tokens * fix bf16 conversion * remove vocab hack * webui ok * support chat parsing for gpt-oss * fix webui * direct mapping mxfp4, FINALLY * force using mxfp4 * properly use lazy tensor * ggml : add mxfp4 ggml : use e8m0 conversion instead of powf Co-authored-by: Diego Devesa <slarengh@gmail.com> change kvalues_mxfp4 table to match e2m1 (#6) metal : remove quantization for now (not used) cuda : fix disabled CUDA graphs due to ffn moe bias vulkan : add support for mxfp4 cont : add cm2 dequant * ggml : add ggml_add_id (#13) * ggml : add ggml_add_id * add cuda impl * llama : add weight support check for add_id * perf opt * add vulkan impl * rename cuda files * add metal impl * allow in-place ggml_add_id * llama : keep biases on CPU with --cpu-moe * llama : fix compile error ggml-ci * cuda : add fallback for __nv_cvt_e8m0_to_bf16raw ggml-ci * cleanup ggml-ci * sycl : fix supports_op for MXFP4 ggml-ci * fix Unknown reasoning format * ggml-cpu : fix AVX build ggml-ci * fix hip build ggml-ci * cuda : add mxfp4 dequantization support for cuBLAS ggml-ci * ggml-cpu : fix mxfp4 fallback definitions for some architectures ggml-ci * cuda : fix version required for __nv_cvt_e8m0_to_bf16raw --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: slaren <slarengh@gmail.com>
75 lines
2.7 KiB
Plaintext
75 lines
2.7 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
|
|
|
|
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);
|