feat: add I2_S GGUF conversion for bitnet-b1.58-2B-4T and refactor T-MAC LUT path

- Add quantize_to_i2_s() for direct ternary-to-I2_S packing in conversion script
- Support offline-quantized models (uint8 packed weights + weight_scale)
- Fix weight_quant double-quantization bug for offline-quantized models
- Fix I2_S scale computation to use first nonzero absolute value
- Add I2_S ftype mapping and BitNetForCausalLM registration
- Refactor ggml-bitnet-lut T-MAC wrapper with proper mul_mat implementation
- Update llama.cpp submodule with I2_S ftype and 2B model type support

src/ggml-bitnet-lut.cpp

@@ -11,6 +11,7 @@
 
 #include "ggml-bitnet.h"
 #include "ggml-quants.h"
+#include "ggml-cpu-impl.h"
 
 #if defined(GGML_BITNET_ARM_TL1) || defined(GGML_BITNET_X86_TL2)
 #include "bitnet-lut-kernels.h"
@@ -19,16 +20,11 @@
 #if defined(GGML_BITNET_ARM_TL1)
 
 void ggml_bitnet_init(void) {
-    // LOG(INFO) << "ggml_bitnet_init";
-
     if (initialized) {
         return;
     }
     initialized = true;
 
-    // if (wrapper == nullptr) {
-    //     wrapper = new BITNET::BITNETGeMMWrapper<bitnet_bitnet_float_type>();
-    // }
     if (bitnet_tensor_extras == nullptr) {
         bitnet_tensor_extras = new bitnet_tensor_extra[GGML_BITNET_MAX_NODES];
     }
@@ -36,26 +32,17 @@ void ggml_bitnet_init(void) {
 }
 
 void ggml_bitnet_free(void) {
-    // LOG(INFO) << "ggml_bitnet_free";
-
     if (!initialized) {
         return;
     }
     initialized = false;
 
-    // delete wrapper;
-    // wrapper = nullptr;
-    for (size_t i = 0; i < bitnet_tensor_extras_index; i++) {
-        // aligned_free(bitnet_tensor_extras[i].qweights);
-        // aligned_free(bitnet_tensor_extras[i].scales);
-    }
     delete[] bitnet_tensor_extras;
     bitnet_tensor_extras = nullptr;
 }
 
 static bool do_permutate(enum ggml_type type) {
     if (type == GGML_TYPE_TL1) {
-        // Add additional args to decide if permuted I2 or naive I2
         return false;
     } else {
         return true;
@@ -65,8 +52,7 @@ static bool do_permutate(enum ggml_type type) {
 bool ggml_bitnet_can_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, const struct ggml_tensor * dst) {
     if ((is_type_supported(src0->type)) &&
         src1->type == GGML_TYPE_F32 &&
-        dst->type == GGML_TYPE_F32 &&
-        src0->backend == GGML_BACKEND_TYPE_CPU) {
+        dst->type == GGML_TYPE_F32) {
         if (src1->ne[1] <= 1) {
             return true;
         }
@@ -79,10 +65,9 @@ size_t ggml_bitnet_mul_mat_get_wsize(const struct ggml_tensor * src0, const stru
     const size_t ne10 = src1->ne[0];
     const size_t ne11 = src1->ne[1];
     const int bits = ggml_bitnet_get_type_bits(src0->type);
-    
+
     size_t wsize = ne10 * ne11 * 15 * sizeof(int8_t) + 1 * ne11 * 2 * sizeof(bitnet_float_type);
     if (sizeof(bitnet_float_type) == 2) {
-        // Need fp32 to fp16 conversion
         wsize += std::max(ne10, ne01) * ne11 * sizeof(bitnet_float_type);
     }
     wsize = ((wsize - 1) / 64 + 1) * 64;
@@ -100,19 +85,61 @@ int ggml_bitnet_get_type_bits(enum ggml_type type) {
     }
 }
 
+void ggml_bitnet_mul_mat(const struct ggml_compute_params * params, struct ggml_tensor * dst) {
+    const struct ggml_tensor * src0 = dst->src[0];
+    const struct ggml_tensor * src1 = dst->src[1];
+
+    const size_t ne00 = src0->ne[0];
+    const size_t ne01 = src0->ne[1];
+    const size_t ne10 = src1->ne[0];
+    const size_t ne11 = src1->ne[1];
+
+    const int ith = params->ith;
+    const int nth = params->nth;
+    const int bits = ggml_bitnet_get_type_bits(src0->type);
+
+    struct bitnet_tensor_extra * extra = (struct bitnet_tensor_extra *)src0->extra;
+    GGML_ASSERT(extra != nullptr);
+
+    char * wdata = (char *)params->wdata;
+    const size_t wsize_per_thread = ggml_bitnet_mul_mat_get_wsize(src0, src1, dst);
+
+    int8_t  * qlut  = (int8_t  *)(wdata);
+    bitnet_float_type * lut_scales = (bitnet_float_type *)(qlut + ne10 * ne11 * 15);
+    bitnet_float_type * lut_biases = (bitnet_float_type *)(lut_scales + ne11);
+
+    if (ith == 0) {
+        ggml_bitnet_mul_mat_task_init(
+            (void *)((char *)src1->data),
+            (void *)qlut,
+            (void *)lut_scales,
+            (void *)lut_biases,
+            ne10, ne00, ne11, bits);
+    }
+
+    // barrier
+    if (nth > 1) {
+        ggml_barrier(params->threadpool);
+    }
+
+    ggml_bitnet_mul_mat_task_compute(
+        (void *)extra->qweights,
+        (void *)extra->scales,
+        (void *)qlut,
+        (void *)lut_scales,
+        (void *)lut_biases,
+        (void *)((char *)dst->data),
+        ne10, ne00, ne11, bits);
+}
+
 #endif
 #if defined(GGML_BITNET_X86_TL2)
 void ggml_bitnet_init(void) {
-    // LOG(INFO) << "ggml_bitnet_init";
-
     if (initialized) {
         return;
     }
     initialized = true;
 
-    // if (wrapper == nullptr) {
-    //     wrapper = new BITNET::BITNETGeMMWrapper<bitnet_bitnet_float_type>();
-    // }
     if (bitnet_tensor_extras == nullptr) {
         bitnet_tensor_extras = new bitnet_tensor_extra[GGML_BITNET_MAX_NODES];
     }
@@ -120,19 +147,11 @@ void ggml_bitnet_init(void) {
 }
 
 void ggml_bitnet_free(void) {
-    // LOG(INFO) << "ggml_bitnet_free";
-
     if (!initialized) {
         return;
     }
     initialized = false;
 
-    // delete wrapper;
-    // wrapper = nullptr;
-    for (size_t i = 0; i < bitnet_tensor_extras_index; i++) {
-        // aligned_free(bitnet_tensor_extras[i].qweights);
-        // aligned_free(bitnet_tensor_extras[i].scales);
-    }
     delete[] bitnet_tensor_extras;
     bitnet_tensor_extras = nullptr;
 }
@@ -140,8 +159,7 @@ void ggml_bitnet_free(void) {
 bool ggml_bitnet_can_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, const struct ggml_tensor * dst) {
     if ((is_type_supported(src0->type)) &&
         src1->type == GGML_TYPE_F32 &&
-        dst->type == GGML_TYPE_F32 &&
-        src0->backend == GGML_BACKEND_TYPE_CPU) {
+        dst->type == GGML_TYPE_F32) {
         return true;
     }
     return false;
@@ -151,10 +169,9 @@ size_t ggml_bitnet_mul_mat_get_wsize(const struct ggml_tensor * src0, const stru
     const size_t ne01 = src0->ne[1];
     const size_t ne10 = src1->ne[0];
     const size_t ne11 = src1->ne[1];
-    
+
     size_t wsize = ne10 * ne11 * 11 * sizeof(int8_t) + 2 * ne11 * 2 * sizeof(bitnet_float_type);
     if (sizeof(bitnet_float_type) == 2) {
-        // Need fp32 to fp16 conversion
         wsize += std::max(ne10, ne01) * ne11 * sizeof(bitnet_float_type);
     }
     wsize = ((wsize - 1) / 64 + 1) * 64;
@@ -171,4 +188,5 @@ int ggml_bitnet_get_type_bits(enum ggml_type type) {
             return 0;
     }
 }
-#endif
+
+#endif