Merge remote-tracking branch 'upstream/concedo'

Makefile

@@ -42,8 +42,8 @@ endif
 #
 
 # keep standard at C11 and C++11
-CFLAGS   = -I. -Iggml/include -Iggml/src -Iinclude -Isrc -I./include -I./include/CL -I./otherarch -I./otherarch/tools -I./otherarch/sdcpp -I./otherarch/sdcpp/thirdparty -I./include/vulkan -O3 -fno-finite-math-only -DNDEBUG -std=c11   -fPIC -DLOG_DISABLE_LOGS -D_GNU_SOURCE -DGGML_USE_LLAMAFILE
-CXXFLAGS = -I. -Iggml/include -Iggml/src -Iinclude -Isrc -I./common -I./include -I./include/CL -I./otherarch -I./otherarch/tools -I./otherarch/sdcpp -I./otherarch/sdcpp/thirdparty -I./include/vulkan -O3 -fno-finite-math-only -DNDEBUG -std=c++11 -fPIC -DLOG_DISABLE_LOGS -D_GNU_SOURCE -DGGML_USE_LLAMAFILE
+CFLAGS   = -I. -Iggml/include -Iggml/src -Iinclude -Isrc -I./include -I./include/CL -I./otherarch -I./otherarch/tools -I./otherarch/sdcpp -I./otherarch/sdcpp/thirdparty -I./include/vulkan -O3 -fno-finite-math-only -fmath-errno -DNDEBUG -std=c11   -fPIC -DLOG_DISABLE_LOGS -D_GNU_SOURCE -DGGML_USE_LLAMAFILE
+CXXFLAGS = -I. -Iggml/include -Iggml/src -Iinclude -Isrc -I./common -I./include -I./include/CL -I./otherarch -I./otherarch/tools -I./otherarch/sdcpp -I./otherarch/sdcpp/thirdparty -I./include/vulkan -O3 -fno-finite-math-only -fmath-errno -DNDEBUG -std=c++11 -fPIC -DLOG_DISABLE_LOGS -D_GNU_SOURCE -DGGML_USE_LLAMAFILE
 LDFLAGS  =
 #CC         := gcc-13
 #CXX        := g++-13
@@ -58,7 +58,7 @@ NONECFLAGS =
 OPENBLAS_FLAGS = -DGGML_USE_OPENBLAS -DGGML_USE_BLAS -I/usr/local/include/openblas
 CLBLAST_FLAGS = -DGGML_USE_CLBLAST
 FAILSAFE_FLAGS = -DUSE_FAILSAFE
-VULKAN_FLAGS = -DGGML_USE_VULKAN
+VULKAN_FLAGS = -DGGML_USE_VULKAN -DSD_USE_VULKAN
 ifdef LLAMA_CUBLAS
 	CUBLAS_FLAGS = -DGGML_USE_CUDA -DSD_USE_CUBLAS
 else
@@ -545,6 +545,9 @@ sdcpp_default.o: otherarch/sdcpp/sdtype_adapter.cpp otherarch/sdcpp/stable-diffu
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 sdcpp_cublas.o: otherarch/sdcpp/sdtype_adapter.cpp otherarch/sdcpp/stable-diffusion.h otherarch/sdcpp/stable-diffusion.cpp otherarch/sdcpp/util.cpp otherarch/sdcpp/upscaler.cpp otherarch/sdcpp/model.cpp otherarch/sdcpp/thirdparty/zip.c
 	$(CXX) $(CXXFLAGS) $(CUBLAS_FLAGS) $(HIPFLAGS) -c $< -o $@
+sdcpp_vulkan.o: otherarch/sdcpp/sdtype_adapter.cpp otherarch/sdcpp/stable-diffusion.h otherarch/sdcpp/stable-diffusion.cpp otherarch/sdcpp/util.cpp otherarch/sdcpp/upscaler.cpp otherarch/sdcpp/model.cpp otherarch/sdcpp/thirdparty/zip.c
+	$(CXX) $(CXXFLAGS) $(VULKAN_FLAGS) -c $< -o $@
+
 
 #whisper objects
 whispercpp_default.o: otherarch/whispercpp/whisper_adapter.cpp
@@ -659,10 +662,10 @@ koboldcpp_hipblas:
 endif
 
 ifdef VULKAN_BUILD
-koboldcpp_vulkan: ggml_v4_vulkan.o ggml_v3.o ggml_v2.o ggml_v1.o expose.o gpttype_adapter_vulkan.o ggml-vulkan.o sdcpp_default.o whispercpp_default.o llavaclip_default.o llava.o ggml-backend_vulkan.o $(OBJS_FULL) $(OBJS)
+koboldcpp_vulkan: ggml_v4_vulkan.o ggml_v3.o ggml_v2.o ggml_v1.o expose.o gpttype_adapter_vulkan.o ggml-vulkan.o sdcpp_vulkan.o whispercpp_default.o llavaclip_default.o llava.o ggml-backend_vulkan.o $(OBJS_FULL) $(OBJS)
 	$(VULKAN_BUILD)
 ifdef NOAVX2_BUILD
-koboldcpp_vulkan_noavx2: ggml_v4_vulkan_noavx2.o ggml_v3_noavx2.o ggml_v2_noavx2.o ggml_v1_failsafe.o expose.o gpttype_adapter_vulkan_noavx2.o ggml-vulkan.o sdcpp_default.o whispercpp_default.o llavaclip_default.o llava.o ggml-backend_vulkan.o $(OBJS_SIMPLE) $(OBJS)
+koboldcpp_vulkan_noavx2: ggml_v4_vulkan_noavx2.o ggml_v3_noavx2.o ggml_v2_noavx2.o ggml_v1_failsafe.o expose.o gpttype_adapter_vulkan_noavx2.o ggml-vulkan.o sdcpp_vulkan.o whispercpp_default.o llavaclip_default.o llava.o ggml-backend_vulkan.o $(OBJS_SIMPLE) $(OBJS)
 	$(VULKAN_BUILD)
 else
 koboldcpp_vulkan_noavx2:

colab.ipynb

@@ -48,7 +48,7 @@
       "source": [
         "#@title <b>v-- Enter your model below and then click this to start Koboldcpp</b>\r\n",
         "\r\n",
-        "Model = \"https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_S.gguf\" #@param [\"https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_S.gguf\",\"https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia-GGUF/resolve/main/LLaMA2-13B-Estopia.Q4_K_S.gguf\",\"https://huggingface.co/mradermacher/Fimbulvetr-11B-v2-GGUF/resolve/main/Fimbulvetr-11B-v2.Q4_K_S.gguf\",\"https://huggingface.co/TheBloke/MythoMax-L2-13B-GGUF/resolve/main/mythomax-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/ReMM-SLERP-L2-13B-GGUF/resolve/main/remm-slerp-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GGUF/resolve/main/xwin-lm-13b-v0.2.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/Stheno-L2-13B-GGUF/resolve/main/stheno-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/MythoMax-L2-Kimiko-v2-13B-GGUF/resolve/main/mythomax-l2-kimiko-v2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/MistRP-Airoboros-7B-GGUF/resolve/main/mistrp-airoboros-7b.Q4_K_S.gguf\",\"https://huggingface.co/TheBloke/airoboros-mistral2.2-7B-GGUF/resolve/main/airoboros-mistral2.2-7b.Q4_K_S.gguf\",\"https://huggingface.co/concedo/KobbleTinyV2-1.1B-GGUF/resolve/main/KobbleTiny-Q4_K.gguf\",\"https://huggingface.co/grimjim/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q8_0.gguf\",\"https://huggingface.co/mradermacher/LemonKunoichiWizardV3-GGUF/resolve/main/LemonKunoichiWizardV3.Q4_K_M.gguf\",\"https://huggingface.co/Lewdiculous/Kunoichi-DPO-v2-7B-GGUF-Imatrix/resolve/main/Kunoichi-DPO-v2-7B-Q4_K_M-imatrix.gguf\",\"https://huggingface.co/mradermacher/L3-8B-Stheno-v3.2-i1-GGUF/resolve/main/L3-8B-Stheno-v3.2.i1-Q4_K_M.gguf\",\"https://huggingface.co/Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix/resolve/main/v2-Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf\",\"https://huggingface.co/bartowski/NeuralDaredevil-8B-abliterated-GGUF/resolve/main/NeuralDaredevil-8B-abliterated-Q4_K_M.gguf\",\"https://huggingface.co/bartowski/L3-8B-Lunaris-v1-GGUF/resolve/main/L3-8B-Lunaris-v1-Q4_K_M.gguf\",\"https://huggingface.co/mradermacher/L3-Umbral-Mind-RP-v2.0-8B-GGUF/resolve/main/L3-Umbral-Mind-RP-v2.0-8B.Q4_K_M.gguf\"]{allow-input: true}\r\n",
+        "Model = \"https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_S.gguf\" #@param [\"https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_S.gguf\",\"https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia-GGUF/resolve/main/LLaMA2-13B-Estopia.Q4_K_S.gguf\",\"https://huggingface.co/mradermacher/Fimbulvetr-11B-v2-GGUF/resolve/main/Fimbulvetr-11B-v2.Q4_K_S.gguf\",\"https://huggingface.co/TheBloke/MythoMax-L2-13B-GGUF/resolve/main/mythomax-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/ReMM-SLERP-L2-13B-GGUF/resolve/main/remm-slerp-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GGUF/resolve/main/xwin-lm-13b-v0.2.Q4_K_M.gguf\",\"https://huggingface.co/mradermacher/mini-magnum-12b-v1.1-GGUF/resolve/main/mini-magnum-12b-v1.1.Q4_K_S.gguf\",\"https://huggingface.co/TheBloke/Stheno-L2-13B-GGUF/resolve/main/stheno-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/MythoMax-L2-Kimiko-v2-13B-GGUF/resolve/main/mythomax-l2-kimiko-v2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/MistRP-Airoboros-7B-GGUF/resolve/main/mistrp-airoboros-7b.Q4_K_S.gguf\",\"https://huggingface.co/TheBloke/airoboros-mistral2.2-7B-GGUF/resolve/main/airoboros-mistral2.2-7b.Q4_K_S.gguf\",\"https://huggingface.co/concedo/KobbleTinyV2-1.1B-GGUF/resolve/main/KobbleTiny-Q4_K.gguf\",\"https://huggingface.co/grimjim/kukulemon-7B-GGUF/resolve/main/kukulemon-7B.Q8_0.gguf\",\"https://huggingface.co/mradermacher/LemonKunoichiWizardV3-GGUF/resolve/main/LemonKunoichiWizardV3.Q4_K_M.gguf\",\"https://huggingface.co/Lewdiculous/Kunoichi-DPO-v2-7B-GGUF-Imatrix/resolve/main/Kunoichi-DPO-v2-7B-Q4_K_M-imatrix.gguf\",\"https://huggingface.co/mradermacher/L3-8B-Stheno-v3.2-i1-GGUF/resolve/main/L3-8B-Stheno-v3.2.i1-Q4_K_M.gguf\",\"https://huggingface.co/Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix/resolve/main/v2-Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf\",\"https://huggingface.co/bartowski/NeuralDaredevil-8B-abliterated-GGUF/resolve/main/NeuralDaredevil-8B-abliterated-Q4_K_M.gguf\",\"https://huggingface.co/bartowski/L3-8B-Lunaris-v1-GGUF/resolve/main/L3-8B-Lunaris-v1-Q4_K_M.gguf\",\"https://huggingface.co/mradermacher/L3-Umbral-Mind-RP-v2.0-8B-GGUF/resolve/main/L3-Umbral-Mind-RP-v2.0-8B.Q4_K_M.gguf\"]{allow-input: true}\r\n",
         "Layers = 99 #@param [99]{allow-input: true}\r\n",
         "ContextSize = 4096 #@param [4096] {allow-input: true}\r\n",
         "#@markdown <hr>\r\n",

common/common.cpp

@@ -1635,7 +1635,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
     options.push_back({ "server",      "       --host HOST",            "ip address to listen (default: %s)", params.hostname.c_str() });
     options.push_back({ "server",      "       --port PORT",            "port to listen (default: %d)", params.port });
     options.push_back({ "server",      "       --path PATH",            "path to serve static files from (default: %s)", params.public_path.c_str() });
-    options.push_back({ "server",      "       --embedding(s)",         "enable embedding endpoint (default: %s)", params.embedding ? "enabled" : "disabled" });
+    options.push_back({ "server",      "       --embedding(s)",         "restrict to only support embedding use case; use only with dedicated embedding models (default: %s)", params.embedding ? "enabled" : "disabled" });
     options.push_back({ "server",      "       --api-key KEY",          "API key to use for authentication (default: none)" });
     options.push_back({ "server",      "       --api-key-file FNAME",   "path to file containing API keys (default: none)" });
     options.push_back({ "server",      "       --ssl-key-file FNAME",   "path to file a PEM-encoded SSL private key" });

examples/save-load-state/save-load-state.cpp

@@ -48,7 +48,7 @@ int main(int argc, char ** argv) {
     // save state (rng, logits, embedding and kv_cache) to file
     {
         std::vector<uint8_t> state_mem(llama_state_get_size(ctx));
-        const size_t written = llama_state_get_data(ctx, state_mem.data());
+        const size_t written = llama_state_get_data(ctx, state_mem.data(), state_mem.size());
 
         FILE *fp_write = fopen("dump_state.bin", "wb");
         fwrite(state_mem.data(), 1, written, fp_write);
@@ -100,13 +100,16 @@ int main(int argc, char ** argv) {
 
     // load state (rng, logits, embedding and kv_cache) from file
     {
-        std::vector<uint8_t> state_mem(llama_state_get_size(ctx2));
+        std::vector<uint8_t> state_mem;
 
         FILE * fp_read = fopen("dump_state.bin", "rb");
+        fseek(fp_read, 0, SEEK_END);
+        state_mem.resize(ftell(fp_read));
+        fseek(fp_read, 0, SEEK_SET);
         const size_t read = fread(state_mem.data(), 1, state_mem.size(), fp_read);
         fclose(fp_read);
 
-        if (read != llama_state_set_data(ctx2, state_mem.data())) {
+        if (read != llama_state_set_data(ctx2, state_mem.data(), state_mem.size())) {
             fprintf(stderr, "\n%s : failed to read state\n", __func__);
             llama_free(ctx2);
             llama_free_model(model);
@@ -160,13 +163,16 @@ int main(int argc, char ** argv) {
 
     // load state (rng, logits, embedding and kv_cache) from file
     {
-        std::vector<uint8_t> state_mem(llama_state_get_size(ctx3));
+        std::vector<uint8_t> state_mem;
 
         FILE * fp_read = fopen("dump_state.bin", "rb");
+        fseek(fp_read, 0, SEEK_END);
+        state_mem.resize(ftell(fp_read));
+        fseek(fp_read, 0, SEEK_SET);
         const size_t read = fread(state_mem.data(), 1, state_mem.size(), fp_read);
         fclose(fp_read);
 
-        if (read != llama_state_set_data(ctx3, state_mem.data())) {
+        if (read != llama_state_set_data(ctx3, state_mem.data(), state_mem.size())) {
             fprintf(stderr, "\n%s : failed to read state\n", __func__);
             llama_free(ctx3);
             llama_free_model(model);
@@ -183,7 +189,7 @@ int main(int argc, char ** argv) {
     {
         // save kv of seq 0
         std::vector<uint8_t> seq_store(llama_state_seq_get_size(ctx3, 0));
-        const size_t ncopy = llama_state_seq_get_data(ctx3, seq_store.data(), 0);
+        const size_t ncopy = llama_state_seq_get_data(ctx3, seq_store.data(), seq_store.size(), 0);
         if (ncopy != seq_store.size()) {
             fprintf(stderr, "\n%s : seq copy data length %zd does not match expected length %zd\n", __func__, ncopy, seq_store.size());
             llama_free(ctx3);
@@ -197,7 +203,7 @@ int main(int argc, char ** argv) {
         fprintf(stderr, "%s : kv cache cleared\n", __func__);
 
         // restore kv into seq 1
-        const size_t nset = llama_state_seq_set_data(ctx3, seq_store.data(), 1);
+        const size_t nset = llama_state_seq_set_data(ctx3, seq_store.data(), seq_store.size(), 1);
         if (nset != seq_store.size()) {
             fprintf(stderr, "\n%s : seq set data length %zd does not match expected length %zd\n", __func__, nset, seq_store.size());
             llama_free(ctx3);

examples/server/README.md

@@ -247,7 +247,7 @@ server:
          --host HOST              ip address to listen (default: 127.0.0.1)
          --port PORT              port to listen (default: 8080)
          --path PATH              path to serve static files from (default: )
-         --embedding(s)           enable embedding endpoint (default: disabled)
+         --embedding(s)           restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)
          --api-key KEY            API key to use for authentication (default: none)
          --api-key-file FNAME     path to file containing API keys (default: none)
          --ssl-key-file FNAME     path to file a PEM-encoded SSL private key

expose.h

@@ -1,11 +1,11 @@
 #pragma once
 #include <cstdint>
 
-const int stop_token_max = 16;
+const int stop_token_max = 24;
 const int ban_token_max = 16;
 const int tensor_split_max = 16;
-const int logit_bias_max = 16;
-const int dry_seq_break_max = 16;
+const int logit_bias_max = 24;
+const int dry_seq_break_max = 24;
 const int images_max = 4;
 
 // match kobold's sampler list and order

ggml/src/ggml-cann/aclnn_ops.cpp

@@ -2381,10 +2381,10 @@ static void ggml_cann_mul_mat_q8_0(ggml_backend_cann_context& ctx,
     size_t input_nb[] = {input_elem_size, input_elem_size * src1->ne[0]};
     size_t input_stride = input_elem_size * src1->ne[0] * src1->ne[1];
 
+    ggml_cann_pool_alloc input_alloctor(ctx.pool());
     if (src1->type != GGML_TYPE_F16) {
         aclTensor* acl_src1_tensor = ggml_cann_create_tensor(src1);
-        ggml_cann_pool_alloc input_alloctor(
-            ctx.pool(), ggml_nelements(src1) * input_elem_size);
+        input_alloctor.alloc(ggml_nelements(src1) * input_elem_size);
         input_buffer = input_alloctor.get();
 
         int64_t* input_cast_ne = src1->ne;

ggml/src/ggml-cuda.cu

@@ -132,7 +132,22 @@ static cudaError_t ggml_cuda_device_malloc(void ** ptr, size_t size, int device)
     }
     return res;
 #else
+
+#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_USE_MUSA)
+    cudaError_t err;
+    if (getenv("GGML_CUDA_ENABLE_UNIFIED_MEMORY") != nullptr)
+    {
+        err = cudaMallocManaged(ptr, size);
+    }
+    else
+    {
+        err = cudaMalloc(ptr, size);
+    }
+    return err;
+#else
     return cudaMalloc(ptr, size);
+#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_USE_MUSA)
+
 #endif
 }
 
@@ -1885,10 +1900,9 @@ static void ggml_cuda_mul_mat_batched_cublas(ggml_backend_cuda_context & ctx, co
 static void ggml_cuda_mul_mat(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
     const bool split = ggml_backend_buffer_is_cuda_split(src0->buffer);
 
-    bool use_dequantize_mul_mat_vec = (ggml_is_quantized(src0->type) || src0->type == GGML_TYPE_F16)
+    bool use_dequantize_mul_mat_vec = ggml_cuda_dmmv_type_supported(src0->type)
         && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
-        && src0->ne[0] % GGML_CUDA_DMMV_X == 0 && src0->ne[0] >= GGML_CUDA_DMMV_X*2
-        && src1->ne[1] == 1;
+        && src0->ne[0] % (GGML_CUDA_DMMV_X*2) == 0 && src1->ne[1] == 1;
     bool          use_mul_mat_vec_q =  ggml_is_quantized(src0->type)
         && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
         && src1->ne[1] <= MMVQ_MAX_BATCH_SIZE;