Revert "PreMerge IK quants and Treillis"

This reverts commit 946c6503dfd1dc5fd5f4f232918d76323ce77e9d.

Author: Nexesenex

examples/quantize/quantize.cpp

@@ -33,8 +33,6 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
     { "Q2_K",     LLAMA_FTYPE_MOSTLY_Q2_K,     " 2.96G, +3.5199 ppl @ Llama-3-8B",  },
     { "Q2_K_S",   LLAMA_FTYPE_MOSTLY_Q2_K_S,   " 2.96G, +3.1836 ppl @ Llama-3-8B",  },
     { "IQ3_XXS",  LLAMA_FTYPE_MOSTLY_IQ3_XXS,  " 3.06 bpw quantization",            },
-    { "IQ3_KT",   LLAMA_FTYPE_MOSTLY_IQ3_KT,   " 3.125 bpw trellis quantization",   },
-    { "IQ4_KT",   LLAMA_FTYPE_MOSTLY_IQ4_KT,   " 4.0 bpw trellis quantization",     },
     { "IQ3_S",    LLAMA_FTYPE_MOSTLY_IQ3_S,    " 3.44 bpw quantization",            },
     { "IQ3_M",    LLAMA_FTYPE_MOSTLY_IQ3_M,    " 3.66 bpw quantization mix",        },
     { "Q3_K",     LLAMA_FTYPE_MOSTLY_Q3_K_M,   "alias for Q3_K_M"                   },
@@ -52,16 +50,6 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
     { "Q5_K_M",   LLAMA_FTYPE_MOSTLY_Q5_K_M,   " 5.33G, +0.0569 ppl @ Llama-3-8B",  },
     { "Q6_K",     LLAMA_FTYPE_MOSTLY_Q6_K,     " 6.14G, +0.0217 ppl @ Llama-3-8B",  },
     { "Q8_0",     LLAMA_FTYPE_MOSTLY_Q8_0,     " 7.96G, +0.0026 ppl @ Llama-3-8B",  },
-    { "IQ4_KS",   LLAMA_FTYPE_MOSTLY_IQ4_KS,   " 4.25 bpw non-linear quantization", },
-    { "IQ4_KSS",  LLAMA_FTYPE_MOSTLY_IQ4_KSS,  " 4.0 bpw non-linear quantization",  },
-    { "IQ2_K",    LLAMA_FTYPE_MOSTLY_IQ2_K,    " 2.375 bpw non-linear quantization",},
-    { "IQ2_KS",   LLAMA_FTYPE_MOSTLY_IQ2_KS,   " 2.1875 bpw non-linear quantization",},
-    { "IQ2_KT",   LLAMA_FTYPE_MOSTLY_IQ2_KT,   " 2.125 bpw trellis quantization",   },
-    { "IQ3_K",    LLAMA_FTYPE_MOSTLY_IQ3_K,    " 3.44 bpw non-linear quantization", },
-    { "IQ3_KL",   LLAMA_FTYPE_MOSTLY_IQ3_KL,   " 4 bpw non-linear quantization mix",},
-    { "IQ4_K",    LLAMA_FTYPE_MOSTLY_IQ4_K,    " 4.5 bpw non-linear quantization",  },
-    { "IQ5_K",    LLAMA_FTYPE_MOSTLY_IQ5_K,    " 5.5 bpw non-linear quantization",  },
-    { "IQ6_K",    LLAMA_FTYPE_MOSTLY_IQ6_K,    " 6.6 bpw non-linear quantization",  },
     { "Q4_0_4_4", LLAMA_FTYPE_MOSTLY_Q4_0_4_4, " 4.34G, +0.4685 ppl @ Llama-3-8B",  },
     { "Q4_0_4_8", LLAMA_FTYPE_MOSTLY_Q4_0_4_8, " 4.34G, +0.4685 ppl @ Llama-3-8B",  },
     { "Q4_0_8_8", LLAMA_FTYPE_MOSTLY_Q4_0_8_8, " 4.34G, +0.4685 ppl @ Llama-3-8B",  },

ggml/include/ggml.h

@@ -397,22 +397,6 @@ extern "C" {
         GGML_TYPE_TQ2_0   = 35,
         //
         GGML_TYPE_Q6_0    = 133,
-        GGML_TYPE_IQ1_BN  = 134,
-        GGML_TYPE_IQ2_BN  = 135,
-        GGML_TYPE_Q8_K64  = 136,
-        GGML_TYPE_IQ2_K   = 137,
-        GGML_TYPE_IQ3_K   = 138,
-        GGML_TYPE_IQ4_K   = 139,
-        GGML_TYPE_IQ5_K   = 140,
-        GGML_TYPE_IQ6_K   = 141,
-        // depricated: GGML_TYPE_IQ2_TN  = 142,
-        // depricated: GGML_TYPE_IQ1_TN  = 143,
-        GGML_TYPE_IQ4_KS  = 144,
-        GGML_TYPE_IQ2_KS  = 145,
-        GGML_TYPE_IQ4_KSS = 146,
-        GGML_TYPE_IQ2_KT  = 147,
-        GGML_TYPE_IQ3_KT  = 148,
-        GGML_TYPE_IQ4_KT  = 149,
         GGML_TYPE_COUNT,
     };
 
@@ -459,21 +443,6 @@ extern "C" {
         GGML_FTYPE_MOSTLY_Q4_0_8_8 = 27, // except 1d tensors
         //
         GGML_FTYPE_MOSTLY_Q6_0    = 127, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ1_BN  = 128, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ2_BN  = 129, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ2_K   = 130, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ3_K   = 131, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ4_K   = 132, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ5_K   = 133, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ6_K   = 134, // except 1d tensors
-        // depricated: GGML_FTYPE_MOSTLY_IQ2_TN  = 135, // except 1d tensors
-        // depricated: GGML_FTYPE_MOSTLY_IQ1_TN  = 136, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ4_KS  = 137, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ2_KS  = 138, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ4_KSS = 139, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ2_KT  = 140, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ3_KT  = 141, // except 1d tensors
-        GGML_FTYPE_MOSTLY_IQ4_KT  = 142, // except 1d tensors
     };
 
     // available tensor operations:

ggml/src/ggml-common.h

@@ -429,89 +429,6 @@ typedef struct {
 } block_iq4_xs;
 static_assert(sizeof(block_iq4_xs) == sizeof(ggml_half) + sizeof(uint16_t) + QK_K/64 + QK_K/2, "wrong iq4_xs block size/padding");
 
-typedef struct {
-    uint8_t  scales[QK_K/32];
-    uint8_t  qs[QK_K/2];
-} block_iq4_ks;
-static_assert(sizeof(block_iq4_ks) == QK_K/32 + QK_K/2, "wrong iq4_ks block size/padding");
-
-typedef struct {
-    uint32_t qs[QK_K/8];
-} block_iq4_kss;
-static_assert(sizeof(block_iq4_kss) == QK_K/8*sizeof(uint32_t), "wrong iq4_kss block size/padding");
-
-typedef struct {
-    ggml_half d;
-    uint16_t extra;
-    uint8_t  scales[QK_K/32];
-    uint8_t  qs[QK_K/4];
-} block_iq2_k;
-static_assert(sizeof(block_iq2_k) == sizeof(ggml_half) + sizeof(uint16_t) + QK_K/32 + QK_K/4, "wrong iq2_k block size/padding");
-
-typedef struct {
-    uint16_t extra;
-    uint8_t  scales[QK_K/64];
-    uint8_t  qs[QK_K/4];
-} block_iq2_ks;
-static_assert(sizeof(block_iq2_ks) == sizeof(uint16_t) + QK_K/64 + QK_K/4, "wrong iq2_ks block size/padding");
-
-typedef struct {
-    uint8_t  scales[QK_K/64];
-    uint8_t  ql[QK_K/4];
-} block_iq2_kt;
-static_assert(sizeof(block_iq2_kt) == QK_K/4 + QK_K/64, "wrong iq2_kt block size/padding");
-
-typedef struct {
-    uint8_t  scales[QK_K/64];
-    uint8_t  ql[QK_K/4];
-    uint8_t  qh[QK_K/8];
-} block_iq3_kt;
-static_assert(sizeof(block_iq3_kt) == QK_K/4 + QK_K/8 + QK_K/64, "wrong iq3_kt block size/padding");
-
-typedef struct {
-    uint32_t qs[QK_K/8];
-} block_iq4_kt;
-static_assert(sizeof(block_iq4_kt) == QK_K/2, "wrong iq4_kt block size/padding");
-
-typedef struct {
-    ggml_half d;
-    uint16_t extra;
-    uint16_t scales_h;
-    uint8_t scales_l[QK_K/32];
-    uint8_t qs[QK_K/4];
-    uint8_t qh[QK_K/8];
-} block_iq3_k;
-static_assert(sizeof(block_iq3_k) == sizeof(ggml_half) + 2*sizeof(uint16_t) + QK_K/32 + QK_K/4 + QK_K/8, "wrong iq3_k block size/padding");
-
-typedef struct {
-    ggml_half d;
-    uint16_t extra;
-    uint8_t  scales_h[QK_K/64];
-    uint8_t  scales_l[QK_K/32];
-    uint8_t  qs[QK_K/2];
-} block_iq4_k;
-static_assert(sizeof(block_iq4_k) == sizeof(ggml_half) + sizeof(uint16_t) + QK_K/2 + 3*QK_K/64, "wrong iq4_k block size/padding");
-
-typedef struct {
-    ggml_half d;
-    uint16_t extra;
-    uint8_t  scales_h[QK_K/64];
-    uint8_t  scales_l[QK_K/32];
-    uint8_t  qs[QK_K/2];
-    uint8_t  qh[QK_K/8];
-} block_iq5_k;
-static_assert(sizeof(block_iq5_k) == sizeof(ggml_half) + sizeof(uint16_t) + QK_K/2 + QK_K/8 + 3*QK_K/64, "wrong iq5_k block size/padding");
-
-typedef struct {
-    ggml_half d;
-    uint16_t extra;
-    int8_t   scales[QK_K/16];
-    uint8_t  qs[QK_K/2];
-    uint8_t  qh[QK_K/4];
-} block_iq6_k;
-static_assert(sizeof(block_iq6_k) == sizeof(ggml_half) + sizeof(uint16_t) + QK_K/2 + QK_K/4 + QK_K/16, "wrong iq6_k block size/padding");
-
-
 #endif // GGML_COMMON_DECL
 #endif // GGML_COMMON_DECL