diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index c98cbcbbe..b87ea76bc 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -10,10 +10,10 @@ on: push: branches: - master - paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp'] + paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu'] pull_request: types: [opened, synchronize, reopened] - paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp'] + paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu'] env: BRANCH_NAME: ${{ github.head_ref || github.ref_name }} diff --git a/CMakeLists.txt b/CMakeLists.txt index 41f5bb737..19cd42dd2 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -432,6 +432,9 @@ target_link_libraries(llama PRIVATE if (BUILD_SHARED_LIBS) set_target_properties(llama PROPERTIES POSITION_INDEPENDENT_CODE ON) target_compile_definitions(llama PRIVATE LLAMA_SHARED LLAMA_BUILD) + if (LLAMA_METAL) + set_target_properties(llama PROPERTIES RESOURCE "${CMAKE_CURRENT_SOURCE_DIR}/ggml-metal.metal") + endif() endif() if (GGML_SOURCES_CUDA) diff --git a/README.md b/README.md index 0c87af6ee..cc3bd5394 100644 --- a/README.md +++ b/README.md @@ -308,7 +308,7 @@ Building the program with BLAS support may lead to some performance improvements - #### BLIS - Check [BLIS.md](BLIS.md) for more information. + Check [BLIS.md](docs/BLIS.md) for more information. - #### Intel MKL diff --git a/SHA256SUMS b/SHA256SUMS index 593c8efaa..ca4d5a4a5 100644 --- a/SHA256SUMS +++ b/SHA256SUMS @@ -1,6 +1,6 @@ 700df0d3013b703a806d2ae7f1bfb8e59814e3d06ae78be0c66368a50059f33d models/7B/consolidated.00.pth 666a4bb533b303bdaf89e1b6a3b6f93535d868de31d903afdc20983dc526c847 models/7B/ggml-model-f16.bin -ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/7B/ggml-model-q4_0.bin +ec2f2d1f0dfb73b72a4cbac7fa121abbe04c37ab327125a38248f930c0f09ddf models/7B/ggml-model-q4_0.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/7B/ggml-model-q4_1.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/7B/ggml-model-q5_0.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/7B/ggml-model-q5_1.bin @@ -8,7 +8,7 @@ ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/7B/ggml 745bf4e29a4dd6f411e72976d92b452da1b49168a4f41c951cfcc8051823cf08 models/13B/consolidated.00.pth d5ccbcc465c71c0de439a5aeffebe8344c68a519bce70bc7f9f92654ee567085 models/13B/consolidated.01.pth 2b206e9b21fb1076f11cafc624e2af97c9e48ea09312a0962153acc20d45f808 models/13B/ggml-model-f16.bin -ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/13B/ggml-model-q4_0.bin +fad169e6f0f575402cf75945961cb4a8ecd824ba4da6be2af831f320c4348fa5 models/13B/ggml-model-q4_0.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/13B/ggml-model-q4_1.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/13B/ggml-model-q5_0.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/13B/ggml-model-q5_1.bin @@ -18,7 +18,7 @@ e23294a58552d8cdec5b7e8abb87993b97ea6eced4178ff2697c02472539d067 models/30B/con 24a87f01028cbd3a12de551dcedb712346c0b5cbdeff1454e0ddf2df9b675378 models/30B/consolidated.02.pth 1adfcef71420886119544949767f6a56cb6339b4d5fcde755d80fe68b49de93b models/30B/consolidated.03.pth 7e1b524061a9f4b27c22a12d6d2a5bf13b8ebbea73e99f218809351ed9cf7d37 models/30B/ggml-model-f16.bin -ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/30B/ggml-model-q4_0.bin +d2a441403944819492ec8c2002cc36fa38468149bfb4b7b4c52afc7bd9a7166d models/30B/ggml-model-q4_0.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/30B/ggml-model-q4_1.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/30B/ggml-model-q5_0.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/30B/ggml-model-q5_1.bin @@ -32,7 +32,7 @@ a287c0dfe49081626567c7fe87f74cce5831f58e459b427b5e05567641f47b78 models/65B/con 72b4eba67a1a3b18cb67a85b70f8f1640caae9b40033ea943fb166bd80a7b36b models/65B/consolidated.06.pth d27f5b0677d7ff129ceacd73fd461c4d06910ad7787cf217b249948c3f3bc638 models/65B/consolidated.07.pth 60758f2384d74e423dffddfd020ffed9d3bb186ebc54506f9c4a787d0f5367b0 models/65B/ggml-model-f16.bin -ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/65B/ggml-model-q4_0.bin +cde053439fa4910ae454407e2717cc46cc2c2b4995c00c93297a2b52e790fa92 models/65B/ggml-model-q4_0.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/65B/ggml-model-q4_1.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/65B/ggml-model-q5_0.bin ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/65B/ggml-model-q5_1.bin diff --git a/examples/common.cpp b/examples/common.cpp index f5d886acf..df69f2736 100644 --- a/examples/common.cpp +++ b/examples/common.cpp @@ -632,6 +632,9 @@ void console_set_color(console_state & con_st, console_color_t color) { case CONSOLE_COLOR_USER_INPUT: fprintf(con_st.out, ANSI_BOLD ANSI_COLOR_GREEN); break; + case CONSOLE_COLOR_ERROR: + fprintf(con_st.out, ANSI_BOLD ANSI_COLOR_RED); + break; } con_st.color = color; fflush(con_st.out); diff --git a/examples/common.h b/examples/common.h index 826e2ae59..6fedb414a 100644 --- a/examples/common.h +++ b/examples/common.h @@ -112,7 +112,8 @@ struct llama_context * llama_init_from_gpt_params(const gpt_params & params); enum console_color_t { CONSOLE_COLOR_DEFAULT=0, CONSOLE_COLOR_PROMPT, - CONSOLE_COLOR_USER_INPUT + CONSOLE_COLOR_USER_INPUT, + CONSOLE_COLOR_ERROR }; struct console_state { diff --git a/examples/main/main.cpp b/examples/main/main.cpp index de63faa3e..66d563143 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -81,6 +81,9 @@ int main(int argc, char ** argv) { if (params.n_ctx > 2048) { fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);" "expect poor results\n", __func__, params.n_ctx); + } else if (params.n_ctx < 8) { + fprintf(stderr, "%s: warning: minimum context size is 8, using minimum size.\n", __func__); + params.n_ctx = 8; } fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT); @@ -331,6 +334,19 @@ int main(int argc, char ** argv) { while ((n_remain != 0 && !is_antiprompt) || params.interactive) { // predict if (embd.size() > 0) { + // Note: n_ctx - 4 here is to match the logic for commandline prompt handling via + // --prompt or --file which uses the same value. + auto max_embd_size = n_ctx - 4; + // Ensure the input doesn't exceed the context size by truncating embd if necessary. + if ((int)embd.size() > max_embd_size) { + auto skipped_tokens = embd.size() - max_embd_size; + console_set_color(con_st, CONSOLE_COLOR_ERROR); + printf("<>", skipped_tokens, skipped_tokens != 1 ? "s" : ""); + console_set_color(con_st, CONSOLE_COLOR_DEFAULT); + fflush(stdout); + embd.resize(max_embd_size); + } + // infinite text generation via context swapping // if we run out of context: // - take the n_keep first tokens from the original prompt (via n_past) diff --git a/flake.nix b/flake.nix index 619100449..f3180c841 100644 --- a/flake.nix +++ b/flake.nix @@ -28,7 +28,7 @@ postPatch = if isM1 then '' substituteInPlace ./ggml-metal.m \ - --replace '[[NSBundle mainBundle] pathForResource:@"ggml-metal" ofType:@"metal"];' "@\"$out/ggml-metal.metal\";" + --replace '[bundle pathForResource:@"ggml-metal" ofType:@"metal"];' "@\"$out/ggml-metal.metal\";" '' else ""; nativeBuildInputs = with pkgs; [ cmake ]; buildInputs = osSpecific; diff --git a/ggml-cuda.cu b/ggml-cuda.cu index a62f26e1e..3b9a5ddfb 100644 --- a/ggml-cuda.cu +++ b/ggml-cuda.cu @@ -1105,6 +1105,9 @@ void * ggml_cuda_host_malloc(size_t size) { void * ptr = nullptr; cudaError_t err = cudaMallocHost((void **) &ptr, size); if (err != cudaSuccess) { + // The allocation error can be bypassed. A null ptr will assigned out of this function. + // This can fixed the OOM error in WSL. + cudaGetLastError(); fprintf(stderr, "WARNING: failed to allocate %.2f MB of pinned memory: %s\n", size/1024.0/1024.0, cudaGetErrorString(err)); return nullptr; @@ -1710,8 +1713,7 @@ void ggml_cuda_nop(const ggml_tensor * src0, const ggml_tensor * src1, ggml_tens (void) dst; } -void ggml_cuda_load_data(const char * fname, struct ggml_tensor * tensor, const size_t offset) { - FILE * fp = fopen(fname, "rb"); +void ggml_cuda_transform_tensor(void * data, struct ggml_tensor * tensor) { int nrows = ggml_nrows(tensor); const size_t nb1 = tensor->nb[1]; ggml_backend backend = tensor->backend; @@ -1745,35 +1747,19 @@ void ggml_cuda_load_data(const char * fname, struct ggml_tensor * tensor, const int64_t nrows_split = row_high - row_low; - const size_t offset_split = offset + row_low*nb1; + const size_t offset_split = row_low*nb1; const size_t size = ggml_nbytes_split(tensor, nrows_split); void * buf; CUDA_CHECK(cudaMalloc(&buf, size)); - void * buf_host = malloc(size); - -#ifdef _WIN32 - int ret = _fseeki64(fp, (__int64) offset_split, SEEK_SET); -#else - int ret = fseek(fp, (long) offset_split, SEEK_SET); -#endif - GGML_ASSERT(ret == 0); // same - - size_t ret2 = fread(buf_host, size, 1, fp); - if (ret2 != 1) { - fprintf(stderr, "unexpectedly reached end of file"); - exit(1); - } + void * buf_host = (char*)data + offset_split; cudaMemcpy(buf, buf_host, size, cudaMemcpyHostToDevice); - cudaDeviceSynchronize(); - free(buf_host); extra->data_device[id] = buf; } tensor->extra = extra; - fclose(fp); } void ggml_cuda_free_data(struct ggml_tensor * tensor) { diff --git a/ggml-cuda.h b/ggml-cuda.h index 3b74e32e2..fde6d4085 100644 --- a/ggml-cuda.h +++ b/ggml-cuda.h @@ -24,7 +24,8 @@ void ggml_cuda_mul_mat(const struct ggml_tensor * src0, const struct ggml_tens void * ggml_cuda_host_malloc(size_t size); void ggml_cuda_host_free(void * ptr); -void ggml_cuda_load_data(const char * fname, struct ggml_tensor * tensors, size_t offset); +void ggml_cuda_transform_tensor(void * data, struct ggml_tensor * tensor); + void ggml_cuda_free_data(struct ggml_tensor * tensor); void ggml_cuda_assign_buffers(struct ggml_tensor * tensor); void ggml_cuda_set_main_device(int main_device); diff --git a/ggml-metal.m b/ggml-metal.m index 167ebd467..658c392e0 100644 --- a/ggml-metal.m +++ b/ggml-metal.m @@ -52,14 +52,18 @@ struct ggml_metal_context { GGML_METAL_DECL_KERNEL(get_rows_q4_0); GGML_METAL_DECL_KERNEL(get_rows_q4_1); GGML_METAL_DECL_KERNEL(get_rows_q2_k); + GGML_METAL_DECL_KERNEL(get_rows_q3_k); GGML_METAL_DECL_KERNEL(get_rows_q4_k); + GGML_METAL_DECL_KERNEL(get_rows_q5_k); GGML_METAL_DECL_KERNEL(get_rows_q6_k); GGML_METAL_DECL_KERNEL(rms_norm); GGML_METAL_DECL_KERNEL(mul_mat_f16_f32); GGML_METAL_DECL_KERNEL(mul_mat_q4_0_f32); GGML_METAL_DECL_KERNEL(mul_mat_q4_1_f32); GGML_METAL_DECL_KERNEL(mul_mat_q2_k_f32); + GGML_METAL_DECL_KERNEL(mul_mat_q3_k_f32); GGML_METAL_DECL_KERNEL(mul_mat_q4_k_f32); + GGML_METAL_DECL_KERNEL(mul_mat_q5_k_f32); GGML_METAL_DECL_KERNEL(mul_mat_q6_k_f32); GGML_METAL_DECL_KERNEL(rope); GGML_METAL_DECL_KERNEL(cpy_f32_f16); @@ -73,6 +77,12 @@ struct ggml_metal_context { // for now it is easier to work in a separate file static NSString * const msl_library_source = @"see metal.metal"; +// Here to assist with NSBundle Path Hack +@interface GGMLMetalClass : NSObject +@end +@implementation GGMLMetalClass +@end + struct ggml_metal_context * ggml_metal_init(void) { fprintf(stderr, "%s: allocating\n", __func__); @@ -80,6 +90,7 @@ struct ggml_metal_context * ggml_metal_init(void) { ctx->device = MTLCreateSystemDefaultDevice(); ctx->queue = [ctx->device newCommandQueue]; + ctx->n_buffers = 0; // determine if we can use MPS if (MPSSupportsMTLDevice(ctx->device)) { @@ -108,7 +119,8 @@ struct ggml_metal_context * ggml_metal_init(void) { NSError * error = nil; //NSString * path = [[NSBundle mainBundle] pathForResource:@"../../examples/metal/metal" ofType:@"metal"]; - NSString * path = [[NSBundle mainBundle] pathForResource:@"ggml-metal" ofType:@"metal"]; + NSBundle * bundle = [NSBundle bundleForClass:[GGMLMetalClass class]]; + NSString * path = [bundle pathForResource:@"ggml-metal" ofType:@"metal"]; fprintf(stderr, "%s: loading '%s'\n", __func__, [path UTF8String]); NSString * src = [NSString stringWithContentsOfFile:path encoding:NSUTF8StringEncoding error:&error]; @@ -145,14 +157,18 @@ struct ggml_metal_context * ggml_metal_init(void) { GGML_METAL_ADD_KERNEL(get_rows_q4_0); GGML_METAL_ADD_KERNEL(get_rows_q4_1); GGML_METAL_ADD_KERNEL(get_rows_q2_k); + GGML_METAL_ADD_KERNEL(get_rows_q3_k); GGML_METAL_ADD_KERNEL(get_rows_q4_k); + GGML_METAL_ADD_KERNEL(get_rows_q5_k); GGML_METAL_ADD_KERNEL(get_rows_q6_k); GGML_METAL_ADD_KERNEL(rms_norm); GGML_METAL_ADD_KERNEL(mul_mat_f16_f32); GGML_METAL_ADD_KERNEL(mul_mat_q4_0_f32); GGML_METAL_ADD_KERNEL(mul_mat_q4_1_f32); GGML_METAL_ADD_KERNEL(mul_mat_q2_k_f32); + GGML_METAL_ADD_KERNEL(mul_mat_q3_k_f32); GGML_METAL_ADD_KERNEL(mul_mat_q4_k_f32); + GGML_METAL_ADD_KERNEL(mul_mat_q5_k_f32); GGML_METAL_ADD_KERNEL(mul_mat_q6_k_f32); GGML_METAL_ADD_KERNEL(rope); GGML_METAL_ADD_KERNEL(cpy_f32_f16); @@ -567,6 +583,15 @@ void ggml_metal_graph_compute( nth1 = 16; [encoder setComputePipelineState:ctx->pipeline_mul_mat_q2_k_f32]; } break; + case GGML_TYPE_Q3_K: + { + GGML_ASSERT(ne02 == 1); + GGML_ASSERT(ne12 == 1); + + nth0 = 4; + nth1 = 16; + [encoder setComputePipelineState:ctx->pipeline_mul_mat_q3_k_f32]; + } break; case GGML_TYPE_Q4_K: { GGML_ASSERT(ne02 == 1); @@ -576,6 +601,15 @@ void ggml_metal_graph_compute( nth1 = 16; [encoder setComputePipelineState:ctx->pipeline_mul_mat_q4_k_f32]; } break; + case GGML_TYPE_Q5_K: + { + GGML_ASSERT(ne02 == 1); + GGML_ASSERT(ne12 == 1); + + nth0 = 4; + nth1 = 16; + [encoder setComputePipelineState:ctx->pipeline_mul_mat_q5_k_f32]; + } break; case GGML_TYPE_Q6_K: { GGML_ASSERT(ne02 == 1); @@ -612,15 +646,14 @@ void ggml_metal_graph_compute( if (src0t == GGML_TYPE_Q4_0 || src0t == GGML_TYPE_Q4_1) { [encoder setThreadgroupMemoryLength:nth0*nth1*sizeof(float) atIndex:0]; [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne11, 1) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)]; - } else if (src0t == GGML_TYPE_Q2_K) { + } + else if (src0t == GGML_TYPE_Q2_K || + src0t == GGML_TYPE_Q3_K || + src0t == GGML_TYPE_Q4_K || + src0t == GGML_TYPE_Q5_K || + src0t == GGML_TYPE_Q6_K) { [encoder setThreadgroupMemoryLength:nth0*nth1*sizeof(float) atIndex:0]; [encoder dispatchThreadgroups:MTLSizeMake(ne01, 1, 1) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)]; - } else if (src0t == GGML_TYPE_Q4_K) { - [encoder setThreadgroupMemoryLength:nth0*nth1*sizeof(float) atIndex:0]; - [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne11, 1) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)]; - } else if (src0t == GGML_TYPE_Q6_K) { - [encoder setThreadgroupMemoryLength:nth0*nth1*sizeof(float) atIndex:0]; - [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne11, 1) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)]; } else { [encoder setThreadgroupMemoryLength:nth0*sizeof(float) atIndex:0]; [encoder dispatchThreadgroups:MTLSizeMake(ne01, ne11, ne12) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)]; @@ -638,7 +671,9 @@ void ggml_metal_graph_compute( case GGML_TYPE_Q4_0: [encoder setComputePipelineState:ctx->pipeline_get_rows_q4_0]; break; case GGML_TYPE_Q4_1: [encoder setComputePipelineState:ctx->pipeline_get_rows_q4_1]; break; case GGML_TYPE_Q2_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q2_k]; break; + case GGML_TYPE_Q3_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q3_k]; break; case GGML_TYPE_Q4_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q4_k]; break; + case GGML_TYPE_Q5_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q5_k]; break; case GGML_TYPE_Q6_K: [encoder setComputePipelineState:ctx->pipeline_get_rows_q6_k]; break; default: GGML_ASSERT(false && "not implemented"); } diff --git a/ggml-metal.metal b/ggml-metal.metal index ccd36386b..09e12a879 100644 --- a/ggml-metal.metal +++ b/ggml-metal.metal @@ -304,34 +304,22 @@ kernel void kernel_mul_mat_q4_0_f32( device const float * src1, device float * dst, constant int64_t & ne00, - constant int64_t & ne01, - constant uint64_t & nb00, - constant uint64_t & nb01, - constant uint64_t & nb02, constant int64_t & ne10, - constant int64_t & ne11, - constant uint64_t & nb10, - constant uint64_t & nb11, - constant uint64_t & nb12, constant int64_t & ne0, - constant int64_t & ne1, threadgroup float * sum [[threadgroup(0)]], uint2 tgpig[[threadgroup_position_in_grid]], - uint2 tpig[[thread_position_in_grid]], uint2 tpitg[[thread_position_in_threadgroup]], uint2 tptg[[threads_per_threadgroup]]) { const int nb = ne00/QK4_0; - const int8_t m8 = 8; - const int64_t r0 = tgpig.x; const int64_t r1 = tgpig.y; device const block_q4_0 * x = (device const block_q4_0 *) src0 + r0*nb; device const float * y = (device const float *) src1 + r1*ne10; - const uint nth = tptg.x*tptg.y; - const uint ith = tptg.y*tpitg.x + tpitg.y; + const int nth = tptg.x*tptg.y; + const int ith = tptg.y*tpitg.x + tpitg.y; const int ix = tpitg.y/4; // 0 or 1 const int iy = tpitg.y - 4*ix; // 0...3 @@ -351,47 +339,32 @@ kernel void kernel_mul_mat_q4_0_f32( for (int j = 0; j < 4; ++j) { - acc[0] += yl[j+ 0] * ((int8_t)(xl[j] & 0xF) - m8); - acc[1] += yl[j+16] * ((int8_t)(xl[j] >> 4) - m8); + acc[0] += yl[j] * (xl[j] & 0xF) + yl[j+16] * (xl[j] >> 4); + acc[1] += yl[j] + yl[j+16]; } - sumf += d * (acc[0] + acc[1]); + sumf += d * (acc[0] - 8.f*acc[1]); } sum[ith] = sumf; // // Accumulate the sum from all threads in the threadgroup - // This version is slightly faster than the commented out one below, - // which I copy-pasted from ggerganov's q4_0 dot product for metal. // threadgroup_barrier(mem_flags::mem_threadgroup); if (ith%4 == 0) { - for (int i = 1; i < 4; ++i) sum[ith] += sum[ith + i]; + sum[ith] += sum[ith+1] + sum[ith+2] + sum[ith+3]; } threadgroup_barrier(mem_flags::mem_threadgroup); if (ith%16 == 0) { - for (int i = 4; i < 16; i += 4) sum[ith] += sum[ith + i]; + sum[ith] += sum[ith+4] + sum[ith+8] + sum[ith+12]; } threadgroup_barrier(mem_flags::mem_threadgroup); if (ith == 0) { - for (int i = 16; i < nth; i += 16) sum[0] += sum[i]; + for (uint i = 16; i < nth; i += 16) sum[0] += sum[i]; dst[r1*ne0 + r0] = sum[0]; } - - //// accumulate the sum from all threads in the threadgroup - //threadgroup_barrier(mem_flags::mem_threadgroup); - //for (uint i = nth/2; i > 0; i /= 2) { - // if (ith < i) { - // sum[ith] += sum[ith + i]; - // } - // threadgroup_barrier(mem_flags::mem_threadgroup); - //} - - //if (ith == 0) { - // dst[r1*ne0 + r0] = sum[0]; - //} } kernel void kernel_mul_mat_q4_1_f32( @@ -399,20 +372,10 @@ kernel void kernel_mul_mat_q4_1_f32( device const float * src1, device float * dst, constant int64_t & ne00, - constant int64_t & ne01, - constant uint64_t & nb00, - constant uint64_t & nb01, - constant uint64_t & nb02, constant int64_t & ne10, - constant int64_t & ne11, - constant uint64_t & nb10, - constant uint64_t & nb11, - constant uint64_t & nb12, constant int64_t & ne0, - constant int64_t & ne1, threadgroup float * sum [[threadgroup(0)]], uint2 tgpig[[threadgroup_position_in_grid]], - uint2 tpig[[thread_position_in_grid]], uint2 tpitg[[thread_position_in_threadgroup]], uint2 tptg[[threads_per_threadgroup]]) { const int nb = ne00/QK4_1; @@ -460,11 +423,11 @@ kernel void kernel_mul_mat_q4_1_f32( // threadgroup_barrier(mem_flags::mem_threadgroup); if (ith%4 == 0) { - for (int i = 1; i < 4; ++i) sum[ith] += sum[ith + i]; + sum[ith] += sum[ith+1] + sum[ith+2] + sum[ith+3]; } threadgroup_barrier(mem_flags::mem_threadgroup); if (ith%16 == 0) { - for (int i = 4; i < 16; i += 4) sum[ith] += sum[ith + i]; + sum[ith] += sum[ith+4] + sum[ith+8] + sum[ith+12]; } threadgroup_barrier(mem_flags::mem_threadgroup); if (ith == 0) { @@ -671,6 +634,15 @@ typedef struct { half d; // super-block scale for quantized scales half dmin; // super-block scale for quantized mins } block_q2_k; +// 84 bytes / block + +typedef struct { + uint8_t hmask[QK_K/8]; // quants - high bit + uint8_t qs[QK_K/4]; // quants - low 2 bits + uint8_t scales[3*QK_K/64]; // scales, quantized with 6 bits + half d; // super-block scale +} block_q3_k; +// 110 bytes / block typedef struct { half d; // super-block scale for quantized scales @@ -678,6 +650,16 @@ typedef struct { uint8_t scales[3*QK_K/64]; // scales and mins, quantized with 6 bits uint8_t qs[QK_K/2]; // 4--bit quants } block_q4_k; +// 144 bytes / block + +typedef struct { + half d; // super-block scale for quantized scales + half dmin; // super-block scale for quantized mins + uint8_t scales[3*QK_K/64]; // scales and mins, quantized with 6 bits + uint8_t qh[QK_K/8]; // quants, high bit + uint8_t qs[QK_K/2]; // quants, low 4 bits +} block_q5_k; +// 176 bytes / block typedef struct { uint8_t ql[QK_K/2]; // quants, lower 4 bits @@ -685,16 +667,19 @@ typedef struct { int8_t scales[QK_K/16]; // scales, quantized with 8 bits half d; // super-block scale } block_q6_k; +// 210 bytes / block static inline uchar4 get_scale_min_k4(int j, device const uint8_t * q) { uchar4 r; if (j < 4) { - r[0] = q[j+0] & 63; r[1] = q[j+4] & 63; - r[2] = q[j+1] & 63; r[3] = q[j+5] & 63; + r[0] = q[j+0] & 63; + r[2] = q[j+1] & 63; + r[1] = q[j+4] & 63; + r[3] = q[j+5] & 63; } else { r[0] = (q[j+4] & 0xF) | ((q[j-4] >> 6) << 4); - r[1] = (q[j+4] >> 4) | ((q[j-0] >> 6) << 4); r[2] = (q[j+5] & 0xF) | ((q[j-3] >> 6) << 4); + r[1] = (q[j+4] >> 4) | ((q[j-0] >> 6) << 4); r[3] = (q[j+5] >> 4) | ((q[j+1] >> 6) << 4); } return r; @@ -735,10 +720,65 @@ static void dequantize_row_q2_k(device const block_q2_k * x, device float * y, i } } +static void dequantize_row_q3_k(device const block_q3_k * x, device float * y, int k) { + assert(k % QK_K == 0); + const int nb = k / QK_K; + + const uint16_t kmask1 = 0x0303; + const uint16_t kmask2 = 0x0f0f; + + uint16_t aux[8]; + thread const int8_t * scales = (thread const int8_t*)aux; + + for (int i = 0; i < nb; i++) { + + const float d_all = (float)(x[i].d); + + device const uint8_t * q = x[i].qs; + device const uint8_t * h = x[i].hmask; + uint8_t m = 1; + + device const uint16_t * a = (device const uint16_t *)x[i].scales; + aux[0] = (a[0] & kmask2) | (((a[4] >> 0) & kmask1) << 4); + aux[1] = (a[1] & kmask2) | (((a[5] >> 0) & kmask1) << 4); + aux[2] = (a[2] & kmask2) | (((a[4] >> 2) & kmask1) << 4); + aux[3] = (a[3] & kmask2) | (((a[5] >> 2) & kmask1) << 4); + aux[4] = ((a[0] >> 4) & kmask2) | (((a[4] >> 4) & kmask1) << 4); + aux[5] = ((a[1] >> 4) & kmask2) | (((a[5] >> 4) & kmask1) << 4); + aux[6] = ((a[2] >> 4) & kmask2) | (((a[4] >> 6) & kmask1) << 4); + aux[7] = ((a[3] >> 4) & kmask2) | (((a[5] >> 6) & kmask1) << 4); + + int is = 0; + float dl; + for (int n = 0; n < QK_K; n += 128) { + int shift = 0; + for (int j = 0; j < 4; ++j) { + + dl = d_all * (scales[is++] - 32); + for (int l = 0; l < 16; ++l) { + *y++ = dl * ((int8_t)((q[l+ 0] >> shift) & 3) - ((h[l+ 0] & m) ? 0 : 4)); + } + + dl = d_all * (scales[is++] - 32); + for (int l = 0; l < 16; ++l) { + *y++ = dl * ((int8_t)((q[l+16] >> shift) & 3) - ((h[l+16] & m) ? 0 : 4)); + } + + shift += 2; + m <<= 1; + } + q += 32; + } + + } + +} + static void dequantize_row_q4_k(device const block_q4_k * x, device float * y, int k) { assert(k % QK_K == 0); const int nb = k / QK_K; + for (int i = 0; i < nb; i++) { const float d = x[i].d; @@ -760,6 +800,33 @@ static void dequantize_row_q4_k(device const block_q4_k * x, device float * y, i } } +static void dequantize_row_q5_k(device const block_q5_k * x, device float * y, int k) { + assert(k % QK_K == 0); + const int nb = k / QK_K; + + for (int i = 0; i < nb; i++) { + + const float d = (float)(x[i].d); + const float min = (float)(x[i].dmin); + + device const uint8_t * ql = x[i].qs; + device const uint8_t * qh = x[i].qh; + + int is = 0; + uint8_t u1 = 1, u2 = 2; + for (int j = 0; j < QK_K; j += 64) { + const uchar4 sc = get_scale_min_k4(is, x[i].scales); + const float d1 = d * sc[0]; const float m1 = min * sc[1]; + const float d2 = d * sc[2]; const float m2 = min * sc[3]; + for (int l = 0; l < 32; ++l) *y++ = d1 * ((ql[l] & 0xF) + (qh[l] & u1 ? 16 : 0)) - m1; + for (int l = 0; l < 32; ++l) *y++ = d2 * ((ql[l] >> 4) + (qh[l] & u2 ? 16 : 0)) - m2; + ql += 32; is += 2; + u1 <<= 2; u2 <<= 2; + } + } + +} + static void dequantize_row_q6_k(device const block_q6_k * x, device float * y, int k) { assert(k % QK_K == 0); const int nb = k / QK_K; @@ -808,6 +875,22 @@ kernel void kernel_get_rows_q2_k( (device float *) ((device char *) dst + i*nb1), ne00); } +kernel void kernel_get_rows_q3_k( + device const void * src0, + device const int * src1, + device float * dst, + constant int64_t & ne00, + constant uint64_t & nb01, + constant uint64_t & nb1, + uint tpig[[thread_position_in_grid]]) { + const int i = tpig; + const int r = ((device int32_t *) src1)[i]; + + dequantize_row_q3_k( + (device const block_q3_k *) ((device char *) src0 + r*nb01), + (device float *) ((device char *) dst + i*nb1), ne00); +} + kernel void kernel_get_rows_q4_k( device const void * src0, device const int * src1, @@ -824,6 +907,22 @@ kernel void kernel_get_rows_q4_k( (device float *) ((device char *) dst + i*nb1), ne00); } +kernel void kernel_get_rows_q5_k( + device const void * src0, + device const int * src1, + device float * dst, + constant int64_t & ne00, + constant uint64_t & nb01, + constant uint64_t & nb1, + uint tpig[[thread_position_in_grid]]) { + const int i = tpig; + const int r = ((device int32_t *) src1)[i]; + + dequantize_row_q5_k( + (device const block_q5_k *) ((device char *) src0 + r*nb01), + (device float *) ((device char *) dst + i*nb1), ne00); +} + kernel void kernel_get_rows_q6_k( device const void * src0, device const int * src1, @@ -847,20 +946,10 @@ kernel void kernel_mul_mat_q2_k_f32( device const float * src1, device float * dst, constant int64_t & ne00, - constant int64_t & ne01, - constant uint64_t & nb00, - constant uint64_t & nb01, - constant uint64_t & nb02, constant int64_t & ne10, - constant int64_t & ne11, - constant uint64_t & nb10, - constant uint64_t & nb11, - constant uint64_t & nb12, constant int64_t & ne0, - constant int64_t & ne1, threadgroup float * sum [[threadgroup(0)]], uint2 tgpig[[threadgroup_position_in_grid]], - uint2 tpig[[thread_position_in_grid]], // we don't use this for now uint2 tpitg[[thread_position_in_threadgroup]], uint2 tptg[[threads_per_threadgroup]]) { @@ -875,7 +964,6 @@ kernel void kernel_mul_mat_q2_k_f32( const int nth = tptg.x*tptg.y; const int ith = tptg.y*tpitg.x + tpitg.y; - const int tid = tpitg.y; // 0...16 const int il = tid/4; // 0...3 const int ir = tid%4; // 0...3 @@ -885,35 +973,54 @@ kernel void kernel_mul_mat_q2_k_f32( const int n = 8; const int is = 4*il + (n*ir)/16; + const int y_offset = 64*il + n*ir; + const int q_offset = 32*ip + n*ir; + sum[ith] = 0.0f; float sumf = 0; for (int i = tpitg.x; i < nb; i += tptg.x) { - device const uint8_t * q = x[i].qs + 32*ip + n*ir; + device const uint8_t * q = x[i].qs + q_offset; device const uint8_t * scales = x[i].scales + is; uint8_t d1 = scales[0] & 0xF; - uint8_t m1 = scales[0] >> 4; uint8_t d2 = scales[2] & 0xF; + uint8_t m1 = scales[0] >> 4; uint8_t m2 = scales[2] >> 4; - device const float * y = yy + i*QK_K + 64*il + n*ir; + device const float * y = yy + i*QK_K + y_offset; + + //float4 s = {0.f, 0.f, 0.f, 0.f}; + float2 s = {0.f, 0.f}; + float smin = 0; + for (int l = 0; l < n; ++l) { + s[0] += y[l+ 0] * ((q[l] >> shift1) & 3); + s[1] += y[l+32] * ((q[l] >> shift2) & 3); + smin += y[l+ 0] * m1 + y[l+32] * m2; + } const float dall = (float)x[i].d; const float dmin = (float)x[i].dmin; - float4 s = {0.f, 0.f, 0.f, 0.f}; - for (int l = 0; l < n; ++l) { - s[0] += y[l+ 0] * ((q[l] >> shift1) & 3); s[1] += y[l+ 0]; - s[2] += y[l+32] * ((q[l] >> shift2) & 3); s[3] += y[l+32]; - } - sumf += dall * (s[0] * d1 + s[2] * d2) - dmin * (s[1] * m1 + s[3] * m2); - + sumf += dall * (s[0] * d1 + s[1] * d2) - dmin * smin; } sum[ith] = sumf; + //int mask1 = (ith%4 == 0); + //int mask2 = (ith%16 == 0); + + //threadgroup_barrier(mem_flags::mem_threadgroup); + //for (int i = 1; i < 4; ++i) sum[ith] += mask1 * sum[ith + i]; + //threadgroup_barrier(mem_flags::mem_threadgroup); + //for (int i = 4; i < 16; i += 4) sum[ith] += mask2 * sum[ith + i]; + //threadgroup_barrier(mem_flags::mem_threadgroup); + //if (ith == 0) { + // for (int i = 16; i < nth; i += 16) sum[0] += sum[i]; + // dst[r1*ne0 + r0] = sum[0]; + //} + // // Accumulate the sum from all threads in the threadgroup // This version is slightly faster than the commented out one below, @@ -932,19 +1039,109 @@ kernel void kernel_mul_mat_q2_k_f32( for (int i = 16; i < nth; i += 16) sum[0] += sum[i]; dst[r1*ne0 + r0] = sum[0]; } +} - //// accumulate the sum from all threads in the threadgroup - //threadgroup_barrier(mem_flags::mem_threadgroup); - //for (uint i = nth/2; i > 0; i /= 2) { - // if (ith < i) { - // sum[ith] += sum[ith + i]; - // } - // threadgroup_barrier(mem_flags::mem_threadgroup); - //} +kernel void kernel_mul_mat_q3_k_f32( + device const void * src0, + device const float * src1, + device float * dst, + constant int64_t & ne00, + constant int64_t & ne10, + constant int64_t & ne0, + constant int64_t & ne1, + threadgroup float * sum [[threadgroup(0)]], + uint2 tgpig[[threadgroup_position_in_grid]], + uint2 tpitg[[thread_position_in_threadgroup]], + uint2 tptg[[threads_per_threadgroup]]) { + + const uint16_t kmask1 = 0x0303; + const uint16_t kmask2 = 0x0f0f; + + const uint8_t m3 = 3; + const int8_t m4 = 4; + + const int nb = ne00/QK_K; + + const int64_t r0 = tgpig.x; + const int64_t r1 = tgpig.y; + + device const block_q3_k * x = (device const block_q3_k *) src0 + r0*nb; + device const float * yy = (device const float *) src1 + r1*ne10; + + const int nth = tptg.x*tptg.y; + const int ith = tptg.y*tpitg.x + tpitg.y; + + const int tid = tpitg.y; // expecting 16 + const int ip = tid/8; // 0 or 1 + const int il = tid/2 - 4*ip; // 0...3 + const int ir = tid%2; + const int n = 8; + const int l0 = n*ir; + + const uint8_t m = 1 << (4*ip + il); + + const int shift = 2*il; + + const uint16_t s_shift1 = 4*ip; + const uint16_t s_shift2 = s_shift1 + 2*(il/2); + const int ik = 4 + (il%2); + + const int q_offset = 32*ip + l0; + const int y_offset = 128*ip + 32*il + l0; + + //float sumf = 0; + float sumf1 = 0, sumf2 = 0; + for (int i = tpitg.x; i < nb; i += tptg.x) { + + const float d_all = (float)(x[i].d); + + device const uint8_t * q = x[i].qs + q_offset; + device const uint8_t * h = x[i].hmask + l0; + device const float * y = yy + i * QK_K + y_offset; + + device const uint16_t * a = (device const uint16_t *)x[i].scales; + const char2 scales = as_type((uint16_t)(((a[il] >> s_shift1) & kmask2) | (((a[ik] >> s_shift2) & kmask1) << 4))); + + float s = 0; + for (int l = 0; l < n; ++l) { + s += y[l+ 0] * ((int8_t)((q[l+ 0] >> shift) & m3) - ((h[l+ 0] & m) ? 0 : m4)); + } + float d = d_all * s; + sumf1 += d * scales[0]; + sumf2 += d; + //sumf += d_all * s * (scales[0] - 32); + + s = 0; + for (int l = 0; l < n; ++l) { + s += y[l+16] * ((int8_t)((q[l+16] >> shift) & m3) - ((h[l+16] & m) ? 0 : m4)); + } + d = d_all * s; + sumf1 += d * scales[1]; + sumf2 += d; + //sumf += d_all * s * (scales[1] - 32); + + } + + //sum[ith] = sumf; + sum[ith] = sumf1 - 32.f*sumf2; + + // + // Accumulate the sum from all threads in the threadgroup + // + threadgroup_barrier(mem_flags::mem_threadgroup); + if (ith%4 == 0) { + for (int i = 1; i < 4; ++i) sum[ith] += sum[ith + i]; + } + threadgroup_barrier(mem_flags::mem_threadgroup); + if (ith%16 == 0) { + for (int i = 4; i < 16; i += 4) sum[ith] += sum[ith + i]; + } + threadgroup_barrier(mem_flags::mem_threadgroup); + if (ith == 0) { + for (int i = 16; i < nth; i += 16) sum[0] += sum[i]; + dst[r1*ne0 + r0] = sum[0]; + } - //if (ith == 0) { - // dst[r1*ne0 + r0] = sum[0]; - //} } kernel void kernel_mul_mat_q4_k_f32( @@ -952,23 +1149,17 @@ kernel void kernel_mul_mat_q4_k_f32( device const float * src1, device float * dst, constant int64_t & ne00, - constant int64_t & ne01, - constant uint64_t & nb00, - constant uint64_t & nb01, - constant uint64_t & nb02, constant int64_t & ne10, - constant int64_t & ne11, - constant uint64_t & nb10, - constant uint64_t & nb11, - constant uint64_t & nb12, constant int64_t & ne0, - constant int64_t & ne1, threadgroup float * sum [[threadgroup(0)]], uint2 tgpig[[threadgroup_position_in_grid]], - uint2 tpig[[thread_position_in_grid]], // we don't use this for now uint2 tpitg[[thread_position_in_threadgroup]], uint2 tptg[[threads_per_threadgroup]]) { + const uint16_t kmask1 = 0x3f3f; + const uint16_t kmask2 = 0x0f0f; + const uint16_t kmask3 = 0xc0c0; + const int nb = ne00/QK_K; const int64_t r0 = tgpig.x; @@ -977,37 +1168,55 @@ kernel void kernel_mul_mat_q4_k_f32( device const block_q4_k * x = (device const block_q4_k *) src0 + r0*nb; device const float * yy = (device const float *) src1 + r1*ne10; - const uint nth = tptg.x*tptg.y; - const uint ith = tptg.y*tpitg.x + tpitg.y; + const int nth = tptg.x*tptg.y; + const int ith = tptg.y*tpitg.x + tpitg.y; const int tid = tpitg.y; // 0...16 const int il = tid/4; // 0...3 - const int ir = tid%4; // 0...3 - const int n = 8; - const int is = 2*il; + const int ir = tid - 4*il;// 0...3 + const int n = 4; + + const int im = il/2; // 0 or 1. 0 computes 0,32 + 128,160, 1 computes 64,96 + 192,224 + const int in = il%2; + + const int l0 = n*(2*ir + in); + const int q_offset = 32*im + l0; + const int y_offset = 64*im + l0; sum[ith] = 0.0f; + uchar2 sc1, sc2, sc3, sc4; + float sumf = 0; for (int i = tpitg.x; i < nb; i += tptg.x) { - device const uint8_t * q = (x + i)->qs + 32*il + n*ir; - device const float * y = yy + i*QK_K + 64*il + n*ir; - device const uint8_t * scales = (x + i)->scales; + device const uint8_t * q1 = (x + i)->qs + q_offset; + device const uint8_t * q2 = q1 + 64; + device const float * y1 = yy + i*QK_K + y_offset; + device const float * y2 = y1 + 128; const float dall = (float)((x + i)->d); const float dmin = (float)((x + i)->dmin); - const uchar4 sc = get_scale_min_k4(is, scales); + device const uint16_t * a = (device const uint16_t *)(x + i)->scales; + sc1 = as_type((uint16_t)(a[im+0] & kmask1)); + sc2 = as_type((uint16_t)(a[im+2] & kmask1)); + sc3 = as_type((uint16_t)(((a[im+4] >> 0) & kmask2) | ((a[im+0] & kmask3) >> 2))); + sc4 = as_type((uint16_t)(((a[im+4] >> 4) & kmask2) | ((a[im+2] & kmask3) >> 2))); float4 s = {0.f, 0.f, 0.f, 0.f}; + float smin = 0; for (int l = 0; l < n; ++l) { - s[0] += y[l+ 0] * (q[l] & 0xF); s[1] += y[l+ 0]; - s[2] += y[l+32] * (q[l] >> 4); s[3] += y[l+32]; + + s[0] += y1[l] * (q1[l] & 0xF); s[1] += y1[l+32] * (q1[l] >> 4); + s[2] += y2[l] * (q2[l] & 0xF); s[3] += y2[l+32] * (q2[l] >> 4); + smin += y1[l] * sc2[0] + y1[l+32] * sc2[1] + y2[l] * sc4[0] + y2[l+32] * sc4[1]; + } - sumf += dall * (s[0] * sc[0] + s[2] * sc[2]) - dmin * (s[1] * sc[1] + s[3] * sc[3]); + sumf += dall * (s[0] * sc1[0] + s[1] * sc1[1] + s[2] * sc3[0] + s[3] * sc3[1]) - dmin * smin; } + sum[ith] = sumf; // @@ -1043,25 +1252,114 @@ kernel void kernel_mul_mat_q4_k_f32( //} } +kernel void kernel_mul_mat_q5_k_f32( + device const void * src0, + device const float * src1, + device float * dst, + constant int64_t & ne00, + constant int64_t & ne10, + constant int64_t & ne0, + threadgroup float * sum [[threadgroup(0)]], + uint2 tgpig[[threadgroup_position_in_grid]], + uint2 tpitg[[thread_position_in_threadgroup]], + uint2 tptg[[threads_per_threadgroup]]) { + + const uint16_t kmask1 = 0x3f3f; + const uint16_t kmask2 = 0x0f0f; + const uint16_t kmask3 = 0xc0c0; + + const int nb = ne00/QK_K; + + const int64_t r0 = tgpig.x; + const int64_t r1 = tgpig.y; + + device const block_q5_k * x = (device const block_q5_k *) src0 + r0*nb; + device const float * yy = (device const float *) src1 + r1*ne10; + + const int nth = tptg.x*tptg.y; + const int ith = tptg.y*tpitg.x + tpitg.y; + + const int tid = tpitg.y; // 0...16 + const int il = tid/4; // 0...3 + const int ir = tid - 4*il;// 0...3 + const int n = 4; + + const int im = il/2; // 0 or 1. 0 computes 0,32 + 128,160, 1 computes 64,96 + 192,224 + const int in = il%2; + + const int l0 = n*(2*ir + in); + const int q_offset = 32*im + l0; + const int y_offset = 64*im + l0; + + const uint8_t hm1 = 1u << (2*im); + const uint8_t hm2 = hm1 << 1; + const uint8_t hm3 = hm1 << 4; + const uint8_t hm4 = hm2 << 4; + + uchar2 sc1, sc2, sc3, sc4; + + float sumf = 0; + for (int i = tpitg.x; i < nb; i += tptg.x) { + + device const uint8_t * q1 = (x + i)->qs + q_offset; + device const uint8_t * q2 = q1 + 64; + device const uint8_t * qh = (x + i)->qh + l0; + device const float * y1 = yy + i*QK_K + y_offset; + device const float * y2 = y1 + 128; + + const float dall = (float)((x + i)->d); + const float dmin = (float)((x + i)->dmin); + + device const uint16_t * a = (device const uint16_t *)(x + i)->scales; + sc1 = as_type((uint16_t)(a[im+0] & kmask1)); + sc2 = as_type((uint16_t)(a[im+2] & kmask1)); + sc3 = as_type((uint16_t)(((a[im+4] >> 0) & kmask2) | ((a[im+0] & kmask3) >> 2))); + sc4 = as_type((uint16_t)(((a[im+4] >> 4) & kmask2) | ((a[im+2] & kmask3) >> 2))); + + float4 s = {0.f, 0.f, 0.f, 0.f}; + float smin = 0; + for (int l = 0; l < n; ++l) { + + s[0] += y1[l+ 0] * ((q1[l] & 0xF) + (qh[l] & hm1 ? 16 : 0)); + s[1] += y1[l+32] * ((q1[l] >> 4) + (qh[l] & hm2 ? 16 : 0)); + s[2] += y2[l+ 0] * ((q2[l] & 0xF) + (qh[l] & hm3 ? 16 : 0)); + s[3] += y2[l+32] * ((q2[l] >> 4) + (qh[l] & hm4 ? 16 : 0)); + smin += y1[l] * sc2[0] + y1[l+32] * sc2[1] + y2[l] * sc4[0] + y2[l+32] * sc4[1]; + + } + sumf += dall * (s[0] * sc1[0] + s[1] * sc1[1] + s[2] * sc3[0] + s[3] * sc3[1]) - dmin * smin; + + } + sum[ith] = sumf; + + // + // Accumulate the sum from all threads in the threadgroup + // + threadgroup_barrier(mem_flags::mem_threadgroup); + if (ith%4 == 0) { + sum[ith] += sum[ith+1] + sum[ith+2] + sum[ith+3]; + } + threadgroup_barrier(mem_flags::mem_threadgroup); + if (ith%16 == 0) { + sum[ith] += sum[ith+4] + sum[ith+8] + sum[ith+12]; + } + threadgroup_barrier(mem_flags::mem_threadgroup); + if (ith == 0) { + for (int i = 16; i < nth; i += 16) sum[0] += sum[i]; + dst[r1*ne0 + r0] = sum[0]; + } + +} + kernel void kernel_mul_mat_q6_k_f32( device const void * src0, device const float * src1, device float * dst, constant int64_t & ne00, - constant int64_t & ne01, - constant uint64_t & nb00, - constant uint64_t & nb01, - constant uint64_t & nb02, constant int64_t & ne10, - constant int64_t & ne11, - constant uint64_t & nb10, - constant uint64_t & nb11, - constant uint64_t & nb12, constant int64_t & ne0, - constant int64_t & ne1, threadgroup float * sum [[threadgroup(0)]], uint2 tgpig[[threadgroup_position_in_grid]], - uint2 tpig[[thread_position_in_grid]], // we don't use this for now uint2 tpitg[[thread_position_in_threadgroup]], uint2 tptg[[threads_per_threadgroup]]) { @@ -1078,24 +1376,29 @@ kernel void kernel_mul_mat_q6_k_f32( device const block_q6_k * x = (device const block_q6_k *) src0 + r0*nb; device const float * yy = (device const float *) src1 + r1*ne10; - const uint nth = tptg.x*tptg.y; - const uint ith = tptg.y*tpitg.x + tpitg.y; + const int nth = tptg.x*tptg.y; + const int ith = tptg.y*tpitg.x + tpitg.y; - const int step = QK_K / tptg.y; // we expect this to be 16 - const int iqs = step * tpitg.y; // 0...240 in steps of 16 + // Note: we absolutely assume that tptg.y = 16 and QK_K = 256! + const int iqs = 16 * tpitg.y; const int ip = iqs / 128; // 0 or 1 const int il = (iqs - 128*ip)/16; // 0...7 const int n = 4; - const int is = 8*ip + (n*il)/16; + const int l0 = n*il; + const int is = 8*ip + l0/16; + + const int y_offset = 128*ip + l0; + const int q_offset_l = 64*ip + l0; + const int q_offset_h = 32*ip + l0; float sumf = 0; for (int i = tpitg.x; i < nb; i += tptg.x) { - device const uint8_t * ql = x[i].ql + 64*ip + n*il; - device const uint8_t * qh = x[i].qh + 32*ip + n*il; + device const uint8_t * ql = x[i].ql + q_offset_l; + device const uint8_t * qh = x[i].qh + q_offset_h; device const int8_t * sc = x[i].scales + is; - device const float * y = yy + i * QK_K + 128*ip + n*il; + device const float * y = yy + i * QK_K + y_offset; const float dall = x[i].d; diff --git a/ggml-opencl.cpp b/ggml-opencl.cpp index 7b6daf4a8..5df922abd 100644 --- a/ggml-opencl.cpp +++ b/ggml-opencl.cpp @@ -1167,7 +1167,7 @@ size_t ggml_cl_mul_mat_get_wsize(const struct ggml_tensor * src0, const struct g return 0; } -void ggml_cl_transform_tensor(ggml_tensor * tensor) { +void ggml_cl_transform_tensor(void * data, ggml_tensor * tensor) { const int64_t ne0 = tensor->ne[0]; const int64_t ne1 = tensor->ne[1]; const int64_t ne2 = tensor->ne[2]; @@ -1179,6 +1179,7 @@ void ggml_cl_transform_tensor(ggml_tensor * tensor) { size_t q_size; cl_mem dst = ggml_cl_pool_malloc(q_sz, &q_size); + tensor->data = data; // copy tensor to device for (int64_t i3 = 0; i3 < ne3; i3++) { for (int64_t i2 = 0; i2 < ne2; i2++) { @@ -1190,35 +1191,5 @@ void ggml_cl_transform_tensor(ggml_tensor * tensor) { CL_CHECK(clFinish(queue)); tensor->data = dst; - tensor->backend = GGML_BACKEND_GPU; -} - -void ggml_cl_load_data(const char * fname, struct ggml_tensor * tensor, const size_t offset) { - cl_int err; - FILE * fp = fopen(fname, "rb"); - - const size_t size = ggml_nbytes(tensor); - - cl_mem dst; - CL_CHECK((dst = clCreateBuffer(context, CL_MEM_READ_ONLY, size, nullptr, &err), err)); - void * buf_host = malloc(size); - -#ifdef _WIN32 - int ret = _fseeki64(fp, (__int64) offset, SEEK_SET); -#else - int ret = fseek(fp, (long) offset, SEEK_SET); -#endif - GGML_ASSERT(ret == 0); // same - - size_t ret2 = fread(buf_host, size, 1, fp); - if (ret2 != 1) { - fprintf(stderr, "unexpectedly reached end of file"); - exit(1); - } - - clEnqueueWriteBuffer(queue, dst, CL_TRUE, 0, size, buf_host, 0, nullptr, nullptr); - - tensor->data = dst; - free(buf_host); - fclose(fp); + GGML_ASSERT(tensor->backend == GGML_BACKEND_GPU); } diff --git a/ggml-opencl.h b/ggml-opencl.h index bf95e5cd0..a92b445c9 100644 --- a/ggml-opencl.h +++ b/ggml-opencl.h @@ -18,8 +18,7 @@ void ggml_cl_host_free(void * ptr); void ggml_cl_free_data(const struct ggml_tensor* tensor); -void ggml_cl_transform_tensor(struct ggml_tensor * tensor); -void ggml_cl_load_data(const char * fname, struct ggml_tensor * tensor, size_t offset); +void ggml_cl_transform_tensor(void * data, struct ggml_tensor * tensor); #ifdef __cplusplus } diff --git a/k_quants.c b/k_quants.c index 4d524494d..a48c82171 100644 --- a/k_quants.c +++ b/k_quants.c @@ -1519,7 +1519,7 @@ void ggml_vec_dot_q4_K_q8_K(const int n, float * restrict s, const void * restri const uint8x16_t m4b = vdupq_n_u8(0xf); #ifdef __ARM_FEATURE_DOTPROD - const uint32x4_t mzero = vdupq_n_s32(0); + const int32x4_t mzero = vdupq_n_s32(0); #endif int8x16x2_t q4bytes; @@ -1745,7 +1745,7 @@ void ggml_vec_dot_q5_K_q8_K(const int n, float * restrict s, const void * restri #ifdef __ARM_NEON const uint8x16_t m4b = vdupq_n_u8(0xf); - const uint32x4_t mzero = vdupq_n_u32(0); + const int32x4_t mzero = vdupq_n_s32(0); const uint8x16_t mone = vdupq_n_u8(1); const uint8x16_t mtwo = vdupq_n_u8(2); @@ -2242,5 +2242,3 @@ void ggml_vec_dot_q6_K_q8_K(const int n, float * restrict s, const void * restri *s = sumf; #endif } - - diff --git a/llama.cpp b/llama.cpp index e100e2bc9..f0f9124d8 100644 --- a/llama.cpp +++ b/llama.cpp @@ -707,6 +707,9 @@ struct llama_model_loader { struct ggml_tensor * get_tensor_for(llama_load_tensor & lt, ggml_backend backend) { struct ggml_tensor * tensor; + if (backend != GGML_BACKEND_CPU) { + ggml_set_no_alloc(ggml_ctx, true); + } if (lt.ne.size() == 2) { tensor = ggml_new_tensor_2d(ggml_ctx, lt.type, lt.ne.at(0), lt.ne.at(1)); } else { @@ -716,6 +719,9 @@ struct llama_model_loader { ggml_set_name(tensor, lt.name.c_str()); LLAMA_ASSERT(lt.ggml_tensor == NULL); // if this fails, we called get_tensor twice on the same tensor + if (backend != GGML_BACKEND_CPU) { + ggml_set_no_alloc(ggml_ctx, use_mmap); + } tensor->backend = backend; lt.ggml_tensor = tensor; num_ggml_tensors_created++; @@ -731,6 +737,7 @@ struct llama_model_loader { void load_all_data(llama_progress_callback progress_callback, void * progress_callback_user_data, llama_mlock * lmlock) { size_t data_size = 0; size_t prefetch_size = 0; + size_t lock_size = 0; for (const llama_load_tensor & lt : tensors_map.tensors) { data_size += lt.size; if (lt.ggml_tensor->backend == GGML_BACKEND_CPU) { @@ -740,11 +747,6 @@ struct llama_model_loader { if (use_mmap) { mapping.reset(new llama_mmap(&file_loaders.at(0)->file, prefetch_size)); - if (!lmlock) { - // Don't call the callback since the actual loading will be lazy - // and we can't measure it. - progress_callback = NULL; - } if (lmlock) { lmlock->init(mapping->addr); } @@ -752,20 +754,49 @@ struct llama_model_loader { size_t done_size = 0; for (llama_load_tensor & lt : tensors_map.tensors) { - if (lt.ggml_tensor->backend != GGML_BACKEND_CPU) { - continue; - } if (progress_callback) { progress_callback((float) done_size / data_size, progress_callback_user_data); } LLAMA_ASSERT(lt.ggml_tensor); // unused tensors should have been caught by load_data already lt.data = (uint8_t *) lt.ggml_tensor->data; - load_data_for(lt); - lt.ggml_tensor->data = lt.data; - done_size += lt.size; - if (use_mmap && lmlock) { - lmlock->grow_to(done_size); + + // allocate temp buffer if not using mmap + if (!use_mmap && lt.data == NULL) { + GGML_ASSERT(lt.ggml_tensor->backend != GGML_BACKEND_CPU); + lt.data = (uint8_t*)malloc(ggml_nbytes(lt.ggml_tensor)); } + + load_data_for(lt); + + switch(lt.ggml_tensor->backend) { + case GGML_BACKEND_CPU: + lt.ggml_tensor->data = lt.data; + if (use_mmap && lmlock) { + lock_size += lt.size; + lmlock->grow_to(lock_size); + } + break; +#if defined(GGML_USE_CUBLAS) + case GGML_BACKEND_GPU: + case GGML_BACKEND_GPU_SPLIT: + ggml_cuda_transform_tensor(lt.data, lt.ggml_tensor); + if (!use_mmap) { + free(lt.data); + } + break; +#elif defined(GGML_USE_CLBLAST) + case GGML_BACKEND_GPU: + ggml_cl_transform_tensor(lt.data, lt.ggml_tensor); + if (!use_mmap) { + free(lt.data); + } + break; +#endif + default: + continue; + } + + done_size += lt.size; } } @@ -1141,7 +1172,7 @@ static void llama_model_load_internal( if (backend == GGML_BACKEND_GPU) { vram_weights += ggml_nbytes(layer.attention_norm) + ggml_nbytes(layer.wq) + ggml_nbytes(layer.wk) + - ggml_nbytes(layer.wv) + ggml_nbytes(layer.wo) + ggml_nbytes(layer.attention_norm) + + ggml_nbytes(layer.wv) + ggml_nbytes(layer.wo) + ggml_nbytes(layer.ffn_norm) + ggml_nbytes(layer.w1) + ggml_nbytes(layer.w2) + ggml_nbytes(layer.w3); } } @@ -1196,58 +1227,14 @@ static void llama_model_load_internal( model.tensors_by_name.emplace_back(lt.name, lt.ggml_tensor); } - ml->load_all_data(progress_callback, progress_callback_user_data, use_mlock ? &lctx.model.mlock_mmap : NULL); - #if defined(GGML_USE_CUBLAS) { ggml_cuda_set_tensor_split(tensor_split); - - size_t done_size = 0; - size_t data_size = 0; - for (llama_load_tensor & lt : ml->tensors_map.tensors) { - data_size += lt.size; - if (lt.ggml_tensor->backend == GGML_BACKEND_CPU) { - done_size += lt.size; - } - } - for (llama_load_tensor & lt : ml->tensors_map.tensors) { - ggml_backend backend = lt.ggml_tensor->backend; - if (backend != GGML_BACKEND_GPU && backend != GGML_BACKEND_GPU_SPLIT) { - continue; - } - if (progress_callback) { - progress_callback((float) done_size / data_size, progress_callback_user_data); - } - ggml_cuda_load_data(fname.c_str(), lt.ggml_tensor, lt.shards.at(0).file_off); - done_size += lt.size; - } } -#elif defined(GGML_USE_CLBLAST) - { - size_t done_size = 0; - size_t data_size = 0; - for (llama_load_tensor & lt : ml->tensors_map.tensors) { - data_size += lt.size; - if (lt.ggml_tensor->backend == GGML_BACKEND_CPU) { - done_size += lt.size; - } - } - for (llama_load_tensor & lt : ml->tensors_map.tensors) { - if (lt.ggml_tensor->backend != GGML_BACKEND_GPU) { - continue; - } - if (progress_callback) { - progress_callback((float) done_size / data_size, progress_callback_user_data); - } - ggml_cl_load_data(fname.c_str(), lt.ggml_tensor, lt.shards.at(0).file_off); - done_size += lt.size; - } - } -#else - (void) n_batch; - (void) tensor_split; #endif + ml->load_all_data(progress_callback, progress_callback_user_data, use_mlock ? &lctx.model.mlock_mmap : NULL); + if (progress_callback) { progress_callback(1.0f, progress_callback_user_data); } @@ -2390,12 +2377,10 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s printf("size = %8.3f MB\n", tensor.size/1024.0/1024.0); } else { new_type = quantized_type; - // TODO: temporary disabled until Metal / OpenCL support is available - // ref: https://github.com/ggerganov/llama.cpp/issues/1711 - //if (tensor.name == "output.weight") { - // new_type = GGML_TYPE_Q6_K; - //} - if (tensor.name.find("attention.wv.weight") != std::string::npos) { + if (tensor.name == "output.weight") { + new_type = GGML_TYPE_Q6_K; + } + else if (tensor.name.find("attention.wv.weight") != std::string::npos) { if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q4_K; else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K; else if ((ftype == LLAMA_FTYPE_MOSTLY_Q4_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q5_K_M) &&