Fix build

Minor edit in ggml.c which originally would prevent OpenCL from loading completely if GGML_USE_ACCELERATE was defined.
Minor speedup in prompt eval time.

.github/workflows/build.yml

@@ -210,6 +210,82 @@ jobs:
           path: |
             llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip
 
+  windows-latest-cmake-cublas:
+    runs-on: windows-latest
+
+    strategy:
+      matrix:
+        cuda: ['12.1.0', '11.7.1']
+        build: ['cublas']
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v1
+
+      - uses: Jimver/cuda-toolkit@v0.2.10
+        id: cuda-toolkit
+        with:
+          cuda: ${{ matrix.cuda }}
+          # TODO(green-sky): _dev seems to fail, and non dev are not enought
+          #sub-packages: '["nvcc", "cudart", "cublas", "cudart_dev", "cublas_dev"]'
+
+      - name: Build
+        id: cmake_build
+        run: |
+          mkdir build
+          cd build
+          cmake .. -DLLAMA_CUBLAS=ON
+          cmake --build . --config Release
+
+      - name: Get commit hash
+        id: commit
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: pr-mpt/actions-commit-hash@v2
+
+      - name: Pack artifacts
+        id: pack_artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        run: |
+          7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\*
+
+      - name: Upload artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
+        with:
+          path: |
+            llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip
+
+      - name: Copy and pack Cuda runtime
+        if: ${{ matrix.cuda == '12.1.0' }}
+        # TODO(green-sky): paths are cuda 12 specific
+        run: |
+          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
+          mkdir '.\build\bin\cudart\'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cudart64_12.dll" '.\build\bin\cudart\'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublas64_12.dll" '.\build\bin\cudart\'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublasLt64_12.dll" '.\build\bin\cudart\'
+          7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip .\build\bin\cudart\*
+
+      - name: Copy and pack Cuda runtime
+        if: ${{ matrix.cuda == '11.7.1' }}
+        # TODO(green-sky): paths are cuda 11 specific
+        run: |
+          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
+          mkdir '.\build\bin\cudart\'
+          ls "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin"
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cudart64_110.dll" '.\build\bin\cudart\'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublas64_11.dll" '.\build\bin\cudart\'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin\cublasLt64_11.dll" '.\build\bin\cudart\'
+          7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip .\build\bin\cudart\*
+
+      - name: Upload Cuda runtime
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
+        with:
+          path: |
+            cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip
+
   release:
     if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
 
@@ -221,6 +297,7 @@ jobs:
       - macOS-latest-make
       - macOS-latest-cmake
       - windows-latest-cmake
+      - windows-latest-cmake-cublas
 
     steps:
       - name: Download artifacts

.gitignore

@@ -21,6 +21,7 @@ build-sanitize-addr/
 build-sanitize-thread/
 
 models/*
+*.bin
 
 /main
 /quantize

Makefile

@@ -107,7 +107,11 @@ ifndef LLAMA_NO_ACCELERATE
 endif
 ifdef LLAMA_OPENBLAS
 	CFLAGS  += -DGGML_USE_OPENBLAS -I/usr/local/include/openblas
-	LDFLAGS += -lopenblas
+	ifneq ($(shell grep -e "Arch Linux" -e "ID_LIKE=arch" /etc/os-release 2>/dev/null),)
+		LDFLAGS += -lopenblas -lcblas
+	else
+		LDFLAGS += -lopenblas
+	endif
 endif
 ifdef LLAMA_CUBLAS
 	CFLAGS    += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
@@ -121,7 +125,12 @@ ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
 endif
 ifdef LLAMA_CLBLAST
 	CFLAGS  += -DGGML_USE_CLBLAST
-	LDFLAGS += -lclblast -lOpenCL
+	# Mac provides OpenCL as a framework
+	ifeq ($(UNAME_S),Darwin)
+		LDFLAGS += -lclblast -framework OpenCL
+	else
+		LDFLAGS += -lclblast -lOpenCL
+	endif
 	OBJS    += ggml-opencl.o
 ggml-opencl.o: ggml-opencl.c ggml-opencl.h
 	$(CC) $(CFLAGS) -c $< -o $@

Package.swift

@@ -2,6 +2,9 @@
 
 import PackageDescription
 
+let unsafeFlags = ["-Wno-shorten-64-to-32", "-I/opt/homebrew/opt/clblast/include"]
+let defines = ["GGML_USE_ACCELERATE", "GGML_USE_CLBLAST"]
+
 let package = Package(
     name: "llama",
     products: [
@@ -11,12 +14,11 @@ let package = Package(
         .target(
             name: "llama",
             path: ".",
-            sources: ["ggml.c", "llama.cpp"],
+            sources: ["ggml.c", "llama.cpp", "ggml-opencl.c"],
             publicHeadersPath: "spm-headers",
-            cSettings: [.unsafeFlags(["-Wno-shorten-64-to-32"]), .define("GGML_USE_ACCELERATE")],
-            linkerSettings: [
-                .linkedFramework("Accelerate")
-            ]
+            cSettings: [.unsafeFlags(unsafeFlags)] + defines.map { .define($0) },
+            cxxSettings: [.unsafeFlags(unsafeFlags)] + defines.map { .define($0) },
+            linkerSettings: [.linkedFramework("Accelerate"), .linkedFramework("OpenCL")]
         ),
     ],
     cxxLanguageStandard: .cxx11

README.md

@@ -18,10 +18,12 @@ The main goal of `llama.cpp` is to run the LLaMA model using 4-bit integer quant
 
 - Plain C/C++ implementation without dependencies
 - Apple silicon first-class citizen - optimized via ARM NEON and Accelerate framework
-- AVX2 support for x86 architectures
+- AVX, AVX2 and AVX512 support for x86 architectures
 - Mixed F16 / F32 precision
-- 4-bit integer quantization support
+- 4-bit, 5-bit and 8-bit integer quantization support
 - Runs on the CPU
+- OpenBLAS support
+- cuBLAS and CLBlast support
 
 The original implementation of `llama.cpp` was [hacked in an evening](https://github.com/ggerganov/llama.cpp/issues/33#issuecomment-1465108022).
 Since then, the project has improved significantly thanks to many contributions. This project is for educational purposes and serves
@@ -43,6 +45,7 @@ as the main playground for developing new features for the [ggml](https://github
 - [X] [Vigogne (French)](https://github.com/bofenghuang/vigogne)
 - [X] [Vicuna](https://github.com/ggerganov/llama.cpp/discussions/643#discussioncomment-5533894)
 - [X] [Koala](https://bair.berkeley.edu/blog/2023/04/03/koala/)
+- [X] [OpenBuddy 🐶 (Multilingual)](https://github.com/OpenBuddy/OpenBuddy)
 
 **Bindings:**
 
@@ -213,7 +216,6 @@ Building the program with BLAS support may lead to some performance improvements
       ```bash
       make LLAMA_OPENBLAS=1
       ```
-      Note: In order to build on Arch Linux with OpenBLAS support enabled you must edit the Makefile adding at the end of the line 105: `-lcblas`
 
     - On Windows:
 

convert.py

@@ -67,6 +67,7 @@ FTYPE_TO_DATA_TYPE: Dict[int, DataType] = \
     {ftype: dtype for (dtype, ftype) in DATA_TYPE_TO_FTYPE.items()}
 
 DATA_TYPE_TO_NUMPY: Dict[DataType, 'np.dtype[Any]'] = {
+    DT_BF16: np.dtype(np.uint16),
     DT_F16: np.dtype(np.float16),
     DT_F32: np.dtype(np.float32),
     DT_I32: np.dtype(np.int32),
@@ -276,6 +277,12 @@ class Tensor(metaclass=ABCMeta):
     def to_ggml(self) -> 'GGMLCompatibleTensor': ...
 
 
+def bf16_to_fp32(bf16_arr: np.ndarray) -> np.ndarray:
+    assert bf16_arr.dtype == np.uint16, f"Input array should be of dtype uint16, but got {bf16_arr.dtype}"
+    fp32_arr = bf16_arr.astype(np.uint32) << 16
+    return fp32_arr.view(np.float32)
+
+
 class UnquantizedTensor(Tensor):
     def __init__(self, ndarray: NDArray) -> None:
         assert isinstance(ndarray, np.ndarray)
@@ -284,6 +291,8 @@ class UnquantizedTensor(Tensor):
 
     def astype(self, data_type: DataType) -> Tensor:
         dtype = DATA_TYPE_TO_NUMPY[data_type]
+        if self.data_type == DT_BF16:
+            self.ndarray = bf16_to_fp32(self.ndarray)
         return UnquantizedTensor(self.ndarray.astype(dtype))
 
     def to_ggml(self) -> 'UnquantizedTensor':
@@ -686,6 +695,7 @@ class LazyUnpickler(pickle.Unpickler):
         description = f'storage data_type={data_type} path-in-zip={filename} path={self.zip_file.filename}'
         return LazyStorage(load=load, kind=pid[1], description=description)
 
+   # @staticmethod
     def lazy_rebuild_tensor_v2(storage: Any, storage_offset: Any, size: Any, stride: Any,  # pyright: ignore[reportSelfClsParameterName]
                                requires_grad: Any, backward_hooks: Any, metadata: Any = None) -> LazyTensor:
         assert isinstance(storage, LazyStorage)
@@ -696,12 +706,18 @@ class LazyUnpickler(pickle.Unpickler):
         description = f'pickled storage_offset={storage_offset} in {storage.description}'
         return LazyTensor(load, list(size), storage.kind.data_type, description)
 
+    # @staticmethod
+    def rebuild_from_type_v2(func, new_type, args, state):
+        return func(*args)
+
     CLASSES: Dict[Any, Any] = {
+        ('torch._tensor', '_rebuild_from_type_v2'): rebuild_from_type_v2,
         ('torch._utils', '_rebuild_tensor_v2'): lazy_rebuild_tensor_v2,
         ('torch', 'BFloat16Storage'): LazyStorageKind(DT_BF16),
         ('torch', 'HalfStorage'): LazyStorageKind(DT_F16),
         ('torch', 'FloatStorage'): LazyStorageKind(DT_F32),
         ('torch', 'IntStorage'): LazyStorageKind(DT_I32),
+        ('torch', 'Tensor'): LazyTensor,
     }
 
     def find_class(self, module: str, name: str) -> Any:
@@ -961,7 +977,7 @@ class OutputFile:
 
 def pick_output_type(model: LazyModel, output_type_str: Optional[str]) -> GGMLFileType:
     wq_type = model["layers.0.attention.wq.weight"].data_type
-    if output_type_str == "f32" or (output_type_str is None and wq_type == DT_F32):
+    if output_type_str == "f32" or (output_type_str is None and wq_type in (DT_F32, DT_BF16)):
         return GGMLFileType.AllF32
     if output_type_str == "f16" or (output_type_str is None and wq_type == DT_F16):
         return GGMLFileType.MostlyF16

examples/main/main.cpp

@@ -444,10 +444,10 @@ int main(int argc, char ** argv) {
                         id = llama_sample_token_mirostat_v2(ctx, &candidates_p, mirostat_tau, mirostat_eta, &mirostat_mu);
                     } else {
                         // Temperature sampling
-                        llama_sample_top_k(ctx, &candidates_p, top_k);
-                        llama_sample_tail_free(ctx, &candidates_p, tfs_z);
-                        llama_sample_typical(ctx, &candidates_p, typical_p);
-                        llama_sample_top_p(ctx, &candidates_p, top_p);
+                        llama_sample_top_k(ctx, &candidates_p, top_k, 1);
+                        llama_sample_tail_free(ctx, &candidates_p, tfs_z, 1);
+                        llama_sample_typical(ctx, &candidates_p, typical_p, 1);
+                        llama_sample_top_p(ctx, &candidates_p, top_p, 1);
                         llama_sample_temperature(ctx, &candidates_p, temp);
                         id = llama_sample_token(ctx, &candidates_p);
                     }

examples/quantize/quantize.cpp

@@ -6,23 +6,47 @@
 #include <map>
 #include <string>
 
-static const std::map<std::string, enum llama_ftype> LLAMA_FTYPE_MAP = {
-  {"q4_0", LLAMA_FTYPE_MOSTLY_Q4_0},
-  {"q4_1", LLAMA_FTYPE_MOSTLY_Q4_1},
-  {"q4_2", LLAMA_FTYPE_MOSTLY_Q4_2},
-  {"q5_0", LLAMA_FTYPE_MOSTLY_Q5_0},
-  {"q5_1", LLAMA_FTYPE_MOSTLY_Q5_1},
-  {"q8_0", LLAMA_FTYPE_MOSTLY_Q8_0},
+static const std::map<std::string, llama_ftype> LLAMA_FTYPE_MAP = {
+    {"q4_0", LLAMA_FTYPE_MOSTLY_Q4_0},
+    {"q4_1", LLAMA_FTYPE_MOSTLY_Q4_1},
+    {"q4_2", LLAMA_FTYPE_MOSTLY_Q4_2},
+    {"q5_0", LLAMA_FTYPE_MOSTLY_Q5_0},
+    {"q5_1", LLAMA_FTYPE_MOSTLY_Q5_1},
+    {"q8_0", LLAMA_FTYPE_MOSTLY_Q8_0},
 };
 
+bool try_parse_ftype(const std::string & ftype_str, llama_ftype & ftype, std::string & ftype_str_out) {
+    auto it = LLAMA_FTYPE_MAP.find(ftype_str);
+    if (it != LLAMA_FTYPE_MAP.end()) {
+        ftype = it->second;
+        ftype_str_out = it->first;
+        return true;
+    }
+    // try to parse as an integer
+    try {
+        int ftype_int = std::stoi(ftype_str);
+        for (auto it = LLAMA_FTYPE_MAP.begin(); it != LLAMA_FTYPE_MAP.end(); it++) {
+            if (it->second == ftype_int) {
+                ftype = it->second;
+                ftype_str_out = it->first;
+                return true;
+            }
+        }
+    }
+    catch (...) {
+        // stoi failed
+    }
+    return false;
+}
+
 // usage:
-//  ./quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type
+//  ./quantize models/llama/ggml-model.bin [models/llama/ggml-model-quant.bin] type [nthreads]
 //
 int main(int argc, char ** argv) {
     ggml_time_init();
 
-    if (argc < 4) {
-        fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type [nthread]\n", argv[0]);
+    if (argc < 3) {
+        fprintf(stderr, "usage: %s model-f32.bin [model-quant.bin] type [nthreads]\n", argv[0]);
         for (auto it = LLAMA_FTYPE_MAP.begin(); it != LLAMA_FTYPE_MAP.end(); it++) {
             fprintf(stderr, "  type = \"%s\" or %d\n", it->first.c_str(), it->second);
         }
@@ -36,24 +60,62 @@ int main(int argc, char ** argv) {
         ggml_free(ctx);
     }
 
+    // parse command line arguments
     const std::string fname_inp = argv[1];
-    const std::string fname_out = argv[2];
+    std::string fname_out;
+    int nthread;
+    llama_ftype ftype;
 
-    enum llama_ftype ftype;
-    if (argv[3][0] == 'q') {
-        auto it = LLAMA_FTYPE_MAP.find(argv[3]);
-        if (it == LLAMA_FTYPE_MAP.end()) {
-            fprintf(stderr, "%s: unknown ftype '%s'\n", __func__, argv[3]);
+    int arg_idx = 2;
+    std::string ftype_str;
+    if (try_parse_ftype(argv[arg_idx], ftype, ftype_str)) {
+        // argv[2] is the ftype
+        std::string fpath;
+        const size_t pos = fname_inp.find_last_of('/');
+        if (pos != std::string::npos) {
+            fpath = fname_inp.substr(0, pos + 1);
+        }
+        // export as [inp path]/ggml-model-[ftype].bin
+        fname_out = fpath + "ggml-model-" + ftype_str + ".bin";
+        arg_idx++;
+    }
+    else {
+        // argv[2] is the output path
+        fname_out = argv[arg_idx];
+        arg_idx++;
+
+        if (argc <= arg_idx) {
+            fprintf(stderr, "%s: missing ftype\n", __func__);
+            return 1;
+        }
+        // argv[3] is the ftype
+        if (!try_parse_ftype(argv[arg_idx], ftype, ftype_str)) {
+            fprintf(stderr, "%s: invalid ftype '%s'\n", __func__, argv[3]);
+            return 1;
+        }
+        arg_idx++;
+    }
+
+    // parse nthreads
+    if (argc > arg_idx) {
+        try {
+            nthread = std::stoi(argv[arg_idx]);
+        }
+        catch (const std::exception & e) {
+            fprintf(stderr, "%s: invalid nthread '%s' (%s)\n", __func__, argv[arg_idx], e.what());
             return 1;
         }
-        ftype = it->second;
     } else {
-        ftype = (enum llama_ftype)atoi(argv[3]);
+        nthread = 0;
     }
 
     fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
 
-    int nthread = argc > 4 ? atoi(argv[4]) : 0;
+    fprintf(stderr, "%s: quantizing '%s' to '%s' as %s", __func__, fname_inp.c_str(), fname_out.c_str(), ftype_str.c_str());
+    if (nthread > 0) {
+        fprintf(stderr, " using %d threads", nthread);
+    }
+    fprintf(stderr, "\n");
 
     const int64_t t_main_start_us = ggml_time_us();
 

ggml.c

@@ -137,6 +137,9 @@ inline static void* ggml_aligned_malloc(size_t size) {
 
 #if defined(GGML_USE_ACCELERATE)
 #include <Accelerate/Accelerate.h>
+#if defined(GGML_USE_CLBLAST) // allow usage of CLBlast alongside Accelerate functions
+#include "ggml-opencl.h"
+#endif
 #elif defined(GGML_USE_OPENBLAS)
 #include <cblas.h>
 #elif defined(GGML_USE_CUBLAS)

llama-util.h

@@ -14,6 +14,7 @@
 
 #include <string>
 #include <vector>
+#include <stdexcept>
 
 #ifdef __has_include
     #if __has_include(<unistd.h>)
@@ -74,7 +75,7 @@ struct llama_file {
     llama_file(const char * fname, const char * mode) {
         fp = std::fopen(fname, mode);
         if (fp == NULL) {
-            throw format("failed to open %s: %s", fname, std::strerror(errno));
+            throw std::runtime_error(format("failed to open %s: %s", fname, strerror(errno)));
         }
         seek(0, SEEK_END);
         size = tell();
@@ -107,10 +108,10 @@ struct llama_file {
         errno = 0;
         std::size_t ret = std::fread(ptr, size, 1, fp);
         if (ferror(fp)) {
-            throw format("read error: %s", strerror(errno));
+            throw std::runtime_error(format("read error: %s", strerror(errno)));
         }
         if (ret != 1) {
-            throw std::string("unexpectedly reached end of file");
+            throw std::runtime_error(std::string("unexpectedly reached end of file"));
         }
     }
 
@@ -133,7 +134,7 @@ struct llama_file {
         errno = 0;
         size_t ret = std::fwrite(ptr, size, 1, fp);
         if (ret != 1) {
-            throw format("write error: %s", strerror(errno));
+            throw std::runtime_error(format("write error: %s", strerror(errno)));
         }
     }
 
@@ -180,7 +181,7 @@ struct llama_mmap {
 #endif
         addr = mmap(NULL, file->size, PROT_READ, flags, fd, 0);
         if (addr == MAP_FAILED) {
-            throw format("mmap failed: %s", strerror(errno));
+            throw std::runtime_error(format("mmap failed: %s", strerror(errno)));
         }
 
         if (prefetch) {
@@ -207,7 +208,7 @@ struct llama_mmap {
         DWORD error = GetLastError();
 
         if (hMapping == NULL) {
-            throw format("CreateFileMappingA failed: %s", llama_format_win_err(error).c_str());
+            throw std::runtime_error(format("CreateFileMappingA failed: %s", llama_format_win_err(error).c_str()));
         }
 
         addr = MapViewOfFile(hMapping, FILE_MAP_READ, 0, 0, 0);
@@ -215,7 +216,7 @@ struct llama_mmap {
         CloseHandle(hMapping);
 
         if (addr == NULL) {
-            throw format("MapViewOfFile failed: %s", llama_format_win_err(error).c_str());
+            throw std::runtime_error(format("MapViewOfFile failed: %s", llama_format_win_err(error).c_str()));
         }
 
         #if _WIN32_WINNT >= _WIN32_WINNT_WIN8
@@ -245,7 +246,7 @@ struct llama_mmap {
 
     llama_mmap(struct llama_file *, bool prefetch = true) {
         (void)prefetch;
-        throw std::string("mmap not supported");
+        throw std::runtime_error(std::string("mmap not supported"));
     }
 #endif
 };

llama.cpp

@@ -1791,7 +1791,7 @@ llama_token llama_sample_token_mirostat(struct llama_context * ctx, llama_token_
     float k = powf((epsilon_hat * powf(2, *mu)) / (1 - powf(N, -epsilon_hat)), 1 / s_hat);
 
     // Sample the next word X using top-k sampling
-    llama_sample_top_k(nullptr, candidates, int(k));
+    llama_sample_top_k(nullptr, candidates, int(k), 1);
     if (ctx) {
         ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
     }

llama.h

@@ -202,16 +202,16 @@ extern "C" {
     LLAMA_API void llama_sample_softmax(struct llama_context * ctx, llama_token_data_array * candidates);
 
     /// @details Top-K sampling described in academic paper "The Curious Case of Neural Text Degeneration" https://arxiv.org/abs/1904.09751
-    LLAMA_API void llama_sample_top_k(struct llama_context * ctx, llama_token_data_array * candidates, int k, size_t min_keep = 1);
+    LLAMA_API void llama_sample_top_k(struct llama_context * ctx, llama_token_data_array * candidates, int k, size_t min_keep);
 
     /// @details Nucleus sampling described in academic paper "The Curious Case of Neural Text Degeneration" https://arxiv.org/abs/1904.09751
-    LLAMA_API void llama_sample_top_p(struct llama_context * ctx, llama_token_data_array * candidates, float p, size_t min_keep = 1);
+    LLAMA_API void llama_sample_top_p(struct llama_context * ctx, llama_token_data_array * candidates, float p, size_t min_keep);
 
     /// @details Tail Free Sampling described in https://www.trentonbricken.com/Tail-Free-Sampling/.
-    LLAMA_API void llama_sample_tail_free(struct llama_context * ctx, llama_token_data_array * candidates, float z, size_t min_keep = 1);
+    LLAMA_API void llama_sample_tail_free(struct llama_context * ctx, llama_token_data_array * candidates, float z, size_t min_keep);
 
     /// @details Locally Typical Sampling implementation described in the paper https://arxiv.org/abs/2202.00666.
-    LLAMA_API void llama_sample_typical(struct llama_context * ctx, llama_token_data_array * candidates, float p, size_t min_keep = 1);
+    LLAMA_API void llama_sample_typical(struct llama_context * ctx, llama_token_data_array * candidates, float p, size_t min_keep);
     LLAMA_API void llama_sample_temperature(struct llama_context * ctx, llama_token_data_array * candidates, float temp);
 
     /// @details Mirostat 1.0 algorithm described in the paper https://arxiv.org/abs/2007.14966. Uses tokens instead of words.

tests/test-sampling.cpp

@@ -32,7 +32,7 @@ void test_top_k(const std::vector<float> & probs,
     llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
     llama_sample_softmax(nullptr, &candidates_p);
     DUMP(&candidates_p);
-    llama_sample_top_k(nullptr, &candidates_p, k);
+    llama_sample_top_k(nullptr, &candidates_p, k, 1);
     DUMP(&candidates_p);
 
     assert(candidates_p.size == expected_probs.size());
@@ -57,7 +57,7 @@ void test_top_p(const std::vector<float> & probs,
     llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
     llama_sample_softmax(nullptr, &candidates_p);
     DUMP(&candidates_p);
-    llama_sample_top_p(nullptr, &candidates_p, p);
+    llama_sample_top_p(nullptr, &candidates_p, p, 1);
     DUMP(&candidates_p);
 
     assert(candidates_p.size == expected_probs.size());
@@ -80,7 +80,7 @@ void test_tfs(const std::vector<float> & probs,
 
     llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
     DUMP(&candidates_p);
-    llama_sample_tail_free(nullptr, &candidates_p, z);
+    llama_sample_tail_free(nullptr, &candidates_p, z, 1);
     DUMP(&candidates_p);
 
     assert(candidates_p.size == expected_probs.size());
@@ -103,7 +103,7 @@ void test_typical(const std::vector<float> & probs,
 
     llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
     DUMP(&candidates_p);
-    llama_sample_typical(nullptr, &candidates_p, p);
+    llama_sample_typical(nullptr, &candidates_p, p, 1);
     DUMP(&candidates_p);
 
     assert(candidates_p.size == expected_probs.size());