Files
enginex-ascend-910-llama.cpp/ggml/src/ggml-cpu/quants.h

98 lines
9.4 KiB
C
Raw Normal View History

ggml-cpu : split arch-specific implementations (#13892) * move ggml-cpu-aarch64 to repack * split quantize_row_q8_0/1 * split helper functions * split ggml_vec_dot_q4_0_q8_0 * split ggml_vec_dot_q4_1_q8_1 * split ggml_vec_dot_q5_0_q8_0 * split ggml_vec_dot_q5_1_q8_1 * split ggml_vec_dot_q8_0_q8_0 * split ggml_vec_dot_tq1_0_q8_K * split ggml_vec_dot_tq2_0_q8_K * split ggml_vec_dot_q2_K_q8_K * split ggml_vec_dot_q3_K_q8_K * split ggml_vec_dot_q4_K_q8_K * split ggml_vec_dot_q5_K_q8_K * split ggml_vec_dot_q6_K_q8_K * split ggml_vec_dot_iq2_xxs_q8_K * split ggml_vec_dot_iq2_xs_q8_K * split ggml_vec_dot_iq2_s_q8_K * split ggml_vec_dot_iq3_xxs_q8_K * split ggml_vec_dot_iq3_s_q8_K * split ggml_vec_dot_iq1_s_q8_K * split ggml_vec_dot_iq1_m_q8_K * split ggml_vec_dot_iq4_nl_q8_0 * split ggml_vec_dot_iq4_xs_q8_K * fix typos * fix missing prototypes * rename ggml-cpu-quants.c * rename ggml-cpu-traits * rename arm folder * move cpu-feats-x86.cpp * rename ggml-cpu-hbm * update arm detection macro in quants.c * move iq quant tables * split ggml_quantize_mat_q8_0/K * split ggml_gemv_* * split ggml_gemm_* * rename namespace aarch64 to repack * use weak aliases to replace test macros * rename GGML_CPU_AARCH64 to GGML_CPU_REPACK * rename more aarch64 to repack * clean up rebase leftover * fix compilation errors * remove trailing spaces * try to fix clang compilation errors * try to fix clang compilation errors again * try to fix clang compilation errors, 3rd attempt * try to fix clang compilation errors, 4th attempt * try to fix clang compilation errors, 5th attempt * try to fix clang compilation errors, 6th attempt * try to fix clang compilation errors, 7th attempt * try to fix clang compilation errors, 8th attempt * try to fix clang compilation errors, 9th attempt * more cleanup * fix compilation errors * fix apple targets * fix a typo in arm version of ggml_vec_dot_q4_K_q8_K Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-06-09 22:47:13 +08:00
#pragma once
#define GGML_COMMON_DECL_C
#include "ggml-common.h"
#include "ggml.h"
// GGML CPU internal header
#ifdef __cplusplus
extern "C" {
#endif
// Quantization
void quantize_row_q4_0(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q4_1(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q5_0(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q5_1(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q8_0(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q8_1(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
llama : add gpt-oss (#15091) * 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>
2025-08-05 22:10:36 +03:00
void quantize_row_mxfp4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
ggml-cpu : split arch-specific implementations (#13892) * move ggml-cpu-aarch64 to repack * split quantize_row_q8_0/1 * split helper functions * split ggml_vec_dot_q4_0_q8_0 * split ggml_vec_dot_q4_1_q8_1 * split ggml_vec_dot_q5_0_q8_0 * split ggml_vec_dot_q5_1_q8_1 * split ggml_vec_dot_q8_0_q8_0 * split ggml_vec_dot_tq1_0_q8_K * split ggml_vec_dot_tq2_0_q8_K * split ggml_vec_dot_q2_K_q8_K * split ggml_vec_dot_q3_K_q8_K * split ggml_vec_dot_q4_K_q8_K * split ggml_vec_dot_q5_K_q8_K * split ggml_vec_dot_q6_K_q8_K * split ggml_vec_dot_iq2_xxs_q8_K * split ggml_vec_dot_iq2_xs_q8_K * split ggml_vec_dot_iq2_s_q8_K * split ggml_vec_dot_iq3_xxs_q8_K * split ggml_vec_dot_iq3_s_q8_K * split ggml_vec_dot_iq1_s_q8_K * split ggml_vec_dot_iq1_m_q8_K * split ggml_vec_dot_iq4_nl_q8_0 * split ggml_vec_dot_iq4_xs_q8_K * fix typos * fix missing prototypes * rename ggml-cpu-quants.c * rename ggml-cpu-traits * rename arm folder * move cpu-feats-x86.cpp * rename ggml-cpu-hbm * update arm detection macro in quants.c * move iq quant tables * split ggml_quantize_mat_q8_0/K * split ggml_gemv_* * split ggml_gemm_* * rename namespace aarch64 to repack * use weak aliases to replace test macros * rename GGML_CPU_AARCH64 to GGML_CPU_REPACK * rename more aarch64 to repack * clean up rebase leftover * fix compilation errors * remove trailing spaces * try to fix clang compilation errors * try to fix clang compilation errors again * try to fix clang compilation errors, 3rd attempt * try to fix clang compilation errors, 4th attempt * try to fix clang compilation errors, 5th attempt * try to fix clang compilation errors, 6th attempt * try to fix clang compilation errors, 7th attempt * try to fix clang compilation errors, 8th attempt * try to fix clang compilation errors, 9th attempt * more cleanup * fix compilation errors * fix apple targets * fix a typo in arm version of ggml_vec_dot_q4_K_q8_K Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-06-09 22:47:13 +08:00
void quantize_row_q2_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q3_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q4_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q5_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q6_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_tq1_0(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_tq2_0(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_iq4_nl (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void quantize_row_iq4_xs (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
// Dot product
void ggml_vec_dot_q4_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q4_1_q8_1(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q5_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q5_1_q8_1(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q8_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
llama : add gpt-oss (#15091) * 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>
2025-08-05 22:10:36 +03:00
void ggml_vec_dot_mxfp4_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
ggml-cpu : split arch-specific implementations (#13892) * move ggml-cpu-aarch64 to repack * split quantize_row_q8_0/1 * split helper functions * split ggml_vec_dot_q4_0_q8_0 * split ggml_vec_dot_q4_1_q8_1 * split ggml_vec_dot_q5_0_q8_0 * split ggml_vec_dot_q5_1_q8_1 * split ggml_vec_dot_q8_0_q8_0 * split ggml_vec_dot_tq1_0_q8_K * split ggml_vec_dot_tq2_0_q8_K * split ggml_vec_dot_q2_K_q8_K * split ggml_vec_dot_q3_K_q8_K * split ggml_vec_dot_q4_K_q8_K * split ggml_vec_dot_q5_K_q8_K * split ggml_vec_dot_q6_K_q8_K * split ggml_vec_dot_iq2_xxs_q8_K * split ggml_vec_dot_iq2_xs_q8_K * split ggml_vec_dot_iq2_s_q8_K * split ggml_vec_dot_iq3_xxs_q8_K * split ggml_vec_dot_iq3_s_q8_K * split ggml_vec_dot_iq1_s_q8_K * split ggml_vec_dot_iq1_m_q8_K * split ggml_vec_dot_iq4_nl_q8_0 * split ggml_vec_dot_iq4_xs_q8_K * fix typos * fix missing prototypes * rename ggml-cpu-quants.c * rename ggml-cpu-traits * rename arm folder * move cpu-feats-x86.cpp * rename ggml-cpu-hbm * update arm detection macro in quants.c * move iq quant tables * split ggml_quantize_mat_q8_0/K * split ggml_gemv_* * split ggml_gemm_* * rename namespace aarch64 to repack * use weak aliases to replace test macros * rename GGML_CPU_AARCH64 to GGML_CPU_REPACK * rename more aarch64 to repack * clean up rebase leftover * fix compilation errors * remove trailing spaces * try to fix clang compilation errors * try to fix clang compilation errors again * try to fix clang compilation errors, 3rd attempt * try to fix clang compilation errors, 4th attempt * try to fix clang compilation errors, 5th attempt * try to fix clang compilation errors, 6th attempt * try to fix clang compilation errors, 7th attempt * try to fix clang compilation errors, 8th attempt * try to fix clang compilation errors, 9th attempt * more cleanup * fix compilation errors * fix apple targets * fix a typo in arm version of ggml_vec_dot_q4_K_q8_K Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-06-09 22:47:13 +08:00
void ggml_vec_dot_q2_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q3_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q4_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q5_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q6_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_tq1_0_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_tq2_0_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq2_xxs_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq2_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq2_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq3_xxs_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq1_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq1_m_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq4_nl_q8_0 (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq4_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
// Generic implementation
void quantize_row_q8_0_generic(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
void quantize_row_q8_1_generic(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
void quantize_row_q8_K_generic(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
void ggml_vec_dot_q4_0_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q4_1_q8_1_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q5_0_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q5_1_q8_1_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q8_0_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
llama : add gpt-oss (#15091) * 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>
2025-08-05 22:10:36 +03:00
void ggml_vec_dot_mxfp4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
ggml-cpu : split arch-specific implementations (#13892) * move ggml-cpu-aarch64 to repack * split quantize_row_q8_0/1 * split helper functions * split ggml_vec_dot_q4_0_q8_0 * split ggml_vec_dot_q4_1_q8_1 * split ggml_vec_dot_q5_0_q8_0 * split ggml_vec_dot_q5_1_q8_1 * split ggml_vec_dot_q8_0_q8_0 * split ggml_vec_dot_tq1_0_q8_K * split ggml_vec_dot_tq2_0_q8_K * split ggml_vec_dot_q2_K_q8_K * split ggml_vec_dot_q3_K_q8_K * split ggml_vec_dot_q4_K_q8_K * split ggml_vec_dot_q5_K_q8_K * split ggml_vec_dot_q6_K_q8_K * split ggml_vec_dot_iq2_xxs_q8_K * split ggml_vec_dot_iq2_xs_q8_K * split ggml_vec_dot_iq2_s_q8_K * split ggml_vec_dot_iq3_xxs_q8_K * split ggml_vec_dot_iq3_s_q8_K * split ggml_vec_dot_iq1_s_q8_K * split ggml_vec_dot_iq1_m_q8_K * split ggml_vec_dot_iq4_nl_q8_0 * split ggml_vec_dot_iq4_xs_q8_K * fix typos * fix missing prototypes * rename ggml-cpu-quants.c * rename ggml-cpu-traits * rename arm folder * move cpu-feats-x86.cpp * rename ggml-cpu-hbm * update arm detection macro in quants.c * move iq quant tables * split ggml_quantize_mat_q8_0/K * split ggml_gemv_* * split ggml_gemm_* * rename namespace aarch64 to repack * use weak aliases to replace test macros * rename GGML_CPU_AARCH64 to GGML_CPU_REPACK * rename more aarch64 to repack * clean up rebase leftover * fix compilation errors * remove trailing spaces * try to fix clang compilation errors * try to fix clang compilation errors again * try to fix clang compilation errors, 3rd attempt * try to fix clang compilation errors, 4th attempt * try to fix clang compilation errors, 5th attempt * try to fix clang compilation errors, 6th attempt * try to fix clang compilation errors, 7th attempt * try to fix clang compilation errors, 8th attempt * try to fix clang compilation errors, 9th attempt * more cleanup * fix compilation errors * fix apple targets * fix a typo in arm version of ggml_vec_dot_q4_K_q8_K Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-06-09 22:47:13 +08:00
void ggml_vec_dot_tq1_0_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_tq2_0_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
llama : add gpt-oss (#15091) * 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>
2025-08-05 22:10:36 +03:00
ggml-cpu : split arch-specific implementations (#13892) * move ggml-cpu-aarch64 to repack * split quantize_row_q8_0/1 * split helper functions * split ggml_vec_dot_q4_0_q8_0 * split ggml_vec_dot_q4_1_q8_1 * split ggml_vec_dot_q5_0_q8_0 * split ggml_vec_dot_q5_1_q8_1 * split ggml_vec_dot_q8_0_q8_0 * split ggml_vec_dot_tq1_0_q8_K * split ggml_vec_dot_tq2_0_q8_K * split ggml_vec_dot_q2_K_q8_K * split ggml_vec_dot_q3_K_q8_K * split ggml_vec_dot_q4_K_q8_K * split ggml_vec_dot_q5_K_q8_K * split ggml_vec_dot_q6_K_q8_K * split ggml_vec_dot_iq2_xxs_q8_K * split ggml_vec_dot_iq2_xs_q8_K * split ggml_vec_dot_iq2_s_q8_K * split ggml_vec_dot_iq3_xxs_q8_K * split ggml_vec_dot_iq3_s_q8_K * split ggml_vec_dot_iq1_s_q8_K * split ggml_vec_dot_iq1_m_q8_K * split ggml_vec_dot_iq4_nl_q8_0 * split ggml_vec_dot_iq4_xs_q8_K * fix typos * fix missing prototypes * rename ggml-cpu-quants.c * rename ggml-cpu-traits * rename arm folder * move cpu-feats-x86.cpp * rename ggml-cpu-hbm * update arm detection macro in quants.c * move iq quant tables * split ggml_quantize_mat_q8_0/K * split ggml_gemv_* * split ggml_gemm_* * rename namespace aarch64 to repack * use weak aliases to replace test macros * rename GGML_CPU_AARCH64 to GGML_CPU_REPACK * rename more aarch64 to repack * clean up rebase leftover * fix compilation errors * remove trailing spaces * try to fix clang compilation errors * try to fix clang compilation errors again * try to fix clang compilation errors, 3rd attempt * try to fix clang compilation errors, 4th attempt * try to fix clang compilation errors, 5th attempt * try to fix clang compilation errors, 6th attempt * try to fix clang compilation errors, 7th attempt * try to fix clang compilation errors, 8th attempt * try to fix clang compilation errors, 9th attempt * more cleanup * fix compilation errors * fix apple targets * fix a typo in arm version of ggml_vec_dot_q4_K_q8_K Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-06-09 22:47:13 +08:00
void ggml_vec_dot_q2_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q3_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q4_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q5_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_q6_K_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq2_xxs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq2_xs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq2_s_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq3_xxs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq3_s_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq1_s_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq1_m_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq4_nl_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
void ggml_vec_dot_iq4_xs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
#ifdef __cplusplus
}
#endif