From affc76edfdefa7b326f526e463cc65ff13fcfb92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Johannes=20G=C3=A4=C3=9Fler?= Date: Sat, 20 May 2023 14:19:28 +0200 Subject: cuda : loading models directly into VRAM, norm calculation on GPU, broadcasting for ggml_mul (#1483) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * Broadcasting for ggml_mul * CUDA kernel for ggml_mul, norms in VRAM * GPU weights not in RAM, direct loading with cuFile * fixup! GPU weights not in RAM, direct loading with cuFile * fixup! GPU weights not in RAM, direct loading with cuFile * define default model path once, sync path with readme (#1366) * ~7% faster Q5_1 AVX2 code (#1477) * convert.py: Support models which are stored in a single pytorch_model.bin (#1469) * Support models in a single pytorch_model.bin * Remove spurious line with typo * benchmark-matmul: Print the average of the test results (#1490) * Remove unused n_parts parameter (#1509) * Fixes #1511 lambda issue for w64devkit (mingw) (#1513) * Fix for w64devkit and mingw * make kv_f16 the default for api users (#1517) * minor : fix compile warnings * readme : adds WizardLM to the list of supported models (#1485) * main : make reverse prompt option act as a stop token in non-interactive mode (#1032) * Make reverse prompt option act as a stop token in non-interactive scenarios * Making requested review changes * Update gpt_params_parse and fix a merge error * Revert "Update gpt_params_parse and fix a merge error" This reverts commit 2bb2ff1748513591ad45b175a75ed1d8089d84c8. * Update gpt_params_parse and fix a merge error take 2 * examples : add persistent chat (#1495) * examples : add persistent chat * examples : fix whitespace --------- Co-authored-by: Georgi Gerganov * tests : add missing header * ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508) * ggml : use F16 instead of F32 in Q4_0, Q4_1 and Q8_0 * llama : bump LLAMA_FILE_VERSION to 3 * cuda : update Q4 and Q8 dequantize kernels * ggml : fix AVX dot products * readme : update performance table + hot topics * ggml : fix scalar implementation of Q4_1 dot * llama : fix compile warnings in llama_set_state_data() * llama : fix name shadowing and C4146 (#1526) * Fix name shadowing and C4146 * Fix if macros not using defined when required * Update llama-util.h Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Update llama-util.h Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Code style Co-authored-by: Georgi Gerganov --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Georgi Gerganov * Fix for mingw (#1462) * llama : add llama_init_backend() API (close #1527) * feature : add blis and other BLAS implementation support (#1502) * feature: add blis support * feature: allow all BLA_VENDOR to be assigned in cmake arguments. align with whisper.cpp pr 927 * fix: version detection for BLA_SIZEOF_INTEGER, recover min version of cmake * Fix typo in INTEGER Co-authored-by: Georgi Gerganov --------- Co-authored-by: Georgi Gerganov * Revert "feature : add blis and other BLAS implementation support (#1502)" This reverts commit 07e9ace0f9da424d82e75df969642522880feb92. * GPU weights not in RAM, direct loading with cuFile * llama : code style fixes + progress print fix * ggml : ggml_mul better broadcast support * cmake : workarounds for cufile when CMake version < 3.25 * gg rebase fixup * Loop in llama.cpp, fixed progress callback * Attempt clang-tidy fix * llama : fix vram size computation * Add forgotten fclose() --------- Co-authored-by: András Salamon Co-authored-by: Ilya Kurdyukov <59548320+ilyakurdyukov@users.noreply.github.com> Co-authored-by: Tom Jobbins <784313+TheBloke@users.noreply.github.com> Co-authored-by: rankaiyx Co-authored-by: Stephan Walter Co-authored-by: DannyDaemonic Co-authored-by: Erik Scholz Co-authored-by: Georgi Gerganov Co-authored-by: David Kennedy Co-authored-by: Jason McCartney Co-authored-by: Evan Jones Co-authored-by: Maxime <672982+maximegmd@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Zenix --- llama-util.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'llama-util.h') diff --git a/llama-util.h b/llama-util.h index a79c5da..3cac9f6 100644 --- a/llama-util.h +++ b/llama-util.h @@ -172,7 +172,7 @@ struct llama_mmap { #ifdef _POSIX_MAPPED_FILES static constexpr bool SUPPORTED = true; - llama_mmap(struct llama_file * file, bool prefetch = true) { + llama_mmap(struct llama_file * file, size_t prefetch = (size_t) -1 /* -1 = max value */) { size = file->size; int fd = fileno(file->fp); int flags = MAP_SHARED; @@ -184,9 +184,9 @@ struct llama_mmap { throw std::runtime_error(format("mmap failed: %s", strerror(errno))); } - if (prefetch) { + if (prefetch > 0) { // Advise the kernel to preload the mapped memory - if (madvise(addr, file->size, MADV_WILLNEED)) { + if (madvise(addr, std::min(file->size, prefetch), MADV_WILLNEED)) { fprintf(stderr, "warning: madvise(.., MADV_WILLNEED) failed: %s\n", strerror(errno)); } -- cgit v1.2.3