List of all items
Structs
Enums
Functions
- dequant_bf16
- dequant_f16
- dequant_iq1_m
- dequant_iq1_s
- dequant_iq2_s
- dequant_iq2_xs
- dequant_iq2_xxs
- dequant_iq3_s
- dequant_iq3_xxs
- dequant_iq4_nl
- dequant_iq4_xs
- dequant_mxfp4_gguf
- dequant_mxfp4_row
- dequant_q2_k
- dequant_q3_k
- dequant_q4_0
- dequant_q4_1
- dequant_q4_k
- dequant_q5_0
- dequant_q5_1
- dequant_q5_k
- dequant_q6_k
- dequant_q8_0
- dequant_q8_1
- dot_iq1_m_f32
- dot_iq1_m_f32_scalar
- dot_iq1_s_f32
- dot_iq1_s_f32_scalar
- dot_iq2_s_f32
- dot_iq2_s_f32_scalar
- dot_iq2_xs_f32
- dot_iq2_xs_f32_scalar
- dot_iq2_xxs_f32
- dot_iq2_xxs_f32_scalar
- dot_iq3_s_f32
- dot_iq3_s_f32_scalar
- dot_iq3_xxs_f32
- dot_iq3_xxs_f32_scalar
- dot_iq4_nl_f32
- dot_iq4_nl_f32_scalar
- dot_iq4_xs_f32
- dot_iq4_xs_f32_scalar
- dot_mxfp4_gguf_f32
- dot_mxfp4_gguf_f32_scalar
- dot_mxfp4_row_f32
- dot_mxfp4_row_f32_scalar
- dot_q2_k_f32
- dot_q2_k_f32_scalar
- dot_q3_k_f32
- dot_q3_k_f32_scalar
- dot_q4_0_f32
- dot_q4_0_f32_scalar
- dot_q4_0_q8
- dot_q4_0_q8_2row
- dot_q4_0_q8_scalar
- dot_q4_1_f32
- dot_q4_1_f32_scalar
- dot_q4_k_f32
- dot_q4_k_f32_scalar
- dot_q4_k_q8
- dot_q4_k_q8_scalar
- dot_q5_0_f32
- dot_q5_0_f32_scalar
- dot_q5_1_f32
- dot_q5_1_f32_scalar
- dot_q5_k_f32
- dot_q5_k_f32_scalar
- dot_q5_k_q8
- dot_q5_k_q8_scalar
- dot_q6_k_f32
- dot_q6_k_f32_scalar
- dot_q6_k_q8
- dot_q6_k_q8_scalar
- dot_q8_0_f32
- dot_q8_0_f32_scalar
- dot_q8_0_q8
- dot_q8_0_q8_scalar
- dot_q8_1_f32
- dot_q8_1_f32_scalar
- gemm_q5_k_q8_row
- gemm_q5_k_q8_row_scalar
- gemm_q6_k_q8_row
- gemm_q6_k_q8_row_scalar
- pack_fp8_kv_blocks
- pack_turbo4_kv_blocks
- quantize_activations_q8
- quantize_activations_q8_k
- quantize_q8_0
- repack::gemm_q4_0x4_group
- repack::gemm_q4_0x4_group_x4
- repack::gemm_q4_kx8_group
- repack::gemm_q4_kx8_group_x4
- repack::gemm_q5_kx8_group
- repack::gemm_q5_kx8_group_x4
- repack::gemm_q6_kx8_group
- repack::gemm_q6_kx8_group_x4
- repack::gemm_q8_0x4_group
- repack::gemm_q8_0x4_group_x4
- repack::gemv_q4_0x4_group
- repack::gemv_q4_0x4_q8_0
- repack::gemv_q4_kx8_group
- repack::gemv_q4_kx8_q8_k
- repack::gemv_q5_kx8_group
- repack::gemv_q5_kx8_q8_k
- repack::gemv_q6_kx8_group
- repack::gemv_q6_kx8_q8_k
- repack::gemv_q8_0x4_group
- repack::gemv_q8_0x4_q8_0
- repack::make_block_q4_0x4
- repack::make_block_q4_kx8
- repack::make_block_q5_kx8
- repack::make_block_q6_kx8
- repack::make_block_q8_0x4
- repack::pack_q4_0_matrix_x4
- repack::pack_q4_k_matrix_x8
- repack::pack_q5_k_matrix_x8
- repack::pack_q6_k_matrix_x8
- repack::pack_q8_0_matrix_x4
- repack::prepare_q8_acts_x4
- repack::prepare_q8_k_acts_x4
- repack::q4_0x4_gemm_uses_acts_x4
- repack::q4_0x4_interleave
- repack::q4_kx8_gemm_uses_acts_x4
- repack::q4_kx8_interleave
- repack::q5_kx8_gemm_uses_acts_x4
- repack::q5_kx8_interleave
- repack::q6_kx8_gemm_uses_acts_x4
- repack::q6_kx8_interleave
- repack::q8_0x4_gemm_uses_acts_x4
- repack::q8_0x4_interleave
- unpack_fp8_kv_blocks
- unpack_turbo4_kv_blocks
Constants
- FP8_KV_BLOCK_BYTES
- FP8_KV_GROUP
- IQ1_M_BLOCK_BYTES
- IQ1_M_BLOCK_ELEMS
- IQ1_S_BLOCK_BYTES
- IQ1_S_BLOCK_ELEMS
- IQ2_S_BLOCK_BYTES
- IQ2_S_BLOCK_ELEMS
- IQ2_XS_BLOCK_BYTES
- IQ2_XS_BLOCK_ELEMS
- IQ2_XXS_BLOCK_BYTES
- IQ2_XXS_BLOCK_ELEMS
- IQ3_S_BLOCK_BYTES
- IQ3_S_BLOCK_ELEMS
- IQ3_XXS_BLOCK_BYTES
- IQ3_XXS_BLOCK_ELEMS
- IQ4_NL_BLOCK_BYTES
- IQ4_NL_BLOCK_ELEMS
- IQ4_XS_BLOCK_BYTES
- IQ4_XS_BLOCK_ELEMS
- MXFP4_GGUF_BLOCK_BYTES
- MXFP4_GGUF_BLOCK_ELEMS
- MXFP4_GROUP_SIZE
- Q2_K_BLOCK_BYTES
- Q2_K_BLOCK_ELEMS
- Q3_K_BLOCK_BYTES
- Q3_K_BLOCK_ELEMS
- Q4_0_BLOCK_BYTES
- Q4_0_BLOCK_ELEMS
- Q4_1_BLOCK_BYTES
- Q4_1_BLOCK_ELEMS
- Q4_K_BLOCK_BYTES
- Q4_K_BLOCK_ELEMS
- Q5_0_BLOCK_BYTES
- Q5_0_BLOCK_ELEMS
- Q5_1_BLOCK_BYTES
- Q5_1_BLOCK_ELEMS
- Q5_K_BLOCK_BYTES
- Q5_K_BLOCK_ELEMS
- Q5_K_GEMM_NC
- Q6_K_BLOCK_BYTES
- Q6_K_BLOCK_ELEMS
- Q6_K_GEMM_NC
- Q8_0_BLOCK_BYTES
- Q8_0_BLOCK_ELEMS
- Q8_1_BLOCK_BYTES
- Q8_1_BLOCK_ELEMS
- TURBO4_KV_BLOCK_BYTES
- TURBO4_KV_GROUP
- iq_tables::IQ1S_GRID
- iq_tables::IQ2S_GRID
- iq_tables::IQ2XS_GRID
- iq_tables::IQ2XXS_GRID
- iq_tables::IQ3S_GRID
- iq_tables::IQ3XXS_GRID
- iq_tables::KMASK_IQ2XS
- iq_tables::KSIGNS_IQ2XS
- repack::Q4_0X4_BLOCK_BYTES
- repack::Q4_0X4_GEMM_NC
- repack::Q4_0X4_INTERLEAVE
- repack::Q4_0X4_NROWS
- repack::Q4_KX8_BLOCK_BYTES
- repack::Q4_KX8_GEMM_NC
- repack::Q4_KX8_NROWS
- repack::Q5_KX8_BLOCK_BYTES
- repack::Q5_KX8_GEMM_NC
- repack::Q5_KX8_NROWS
- repack::Q6_KX8_BLOCK_BYTES
- repack::Q6_KX8_GEMM_NC
- repack::Q6_KX8_NROWS
- repack::Q8K_ACTS_X4_NC
- repack::Q8_0X4_BLOCK_BYTES
- repack::Q8_0X4_GEMM_NC
- repack::Q8_0X4_INTERLEAVE
- repack::Q8_0X4_NROWS