aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-04-18ggml : add new Q4_2 quantization (ARM only) (#1046)Georgi Gerganov
* ggml : Q4_2 ARM * ggml : add ggml_is_quantized() * llama : update llama_type_name() with Q4_2 entry * ggml : speed-up q4_2 - 4 threads: ~100ms -> ~90ms - 8 threads: ~55ms -> ~50ms * ggml : optimize q4_2 using vmlaq_n_f32 + vmulq_n_f32
2023-04-18ggml : scratch that - vmlaq_n_f32 is always betterGeorgi Gerganov
Had a background process that was messing with the timings
2023-04-18gitignore : vdotGeorgi Gerganov
2023-04-18ggml : optimize ggml_vec_dot_q4_0_q8_0() using vectorized accumulatorsGeorgi Gerganov
2023-04-18Adding a simple program to measure speed of dot products (#1041)Kawrakow
On my Mac, the direct Q4_1 product is marginally slower (~69 vs ~55 us for Q4_0). The SIMD-ified ggml version is now almost 2X slower (~121 us). On a Ryzen 7950X CPU, the direct product for Q4_1 quantization is faster than the AVX2 implementation (~60 vs ~62 us). --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-04-18readme : update hot topics about new LoRA functionalityGeorgi Gerganov
2023-04-18ci : do not run on draftsGeorgi Gerganov
2023-04-18Do not close file after mmap (Windows version) (#1034)Ivan Komarov
2023-04-17readme : add Ruby bindings (#1029)Atsushi Tatsuma
2023-04-17add 4_0 to default outfile namestr dict (#1031)Cameron
this came up when trying to convert the gpt4all-lora-unfiltered-quantized.bin file
2023-04-17Add LoRA support (#820)slaren
2023-04-17llama : well-defined static initialization of complex objects (#927)Arik Poznanski
* Replaced static initialization of complex objects with a initialization on first use. This prevents an undefined behavior on program run, for example, crash in Release build, works in Debug build * replaced use of auto with exact type to avoid using -std=c++14 * Made the assessors functions for static maps be static const
2023-04-17quantize-stats : fix bug in --type argumentGeorgi Gerganov
2023-04-17ggml : avoid using ggml_fp16_to_fp32() and ggml_fp32_to_fp16() in ggml.cGeorgi Gerganov
2023-04-17Speedup the AVX-512 implementation of ggml_vec_dot_q4_0() (#933)Ivan Komarov
2023-04-16Fix: do not close file on mmap (#1017)slaren
2023-04-16stdout : vertical align outputs for better readibilityGeorgi Gerganov
2023-04-16examples: add missing <ctime> include for time() (#1011)Pavol Rusnak
2023-04-16Fix msys2 build error and warnings (#1009)nanahi
2023-04-15convert.py: Fix loading safetensors and ggml format on Windows (#991)comex
Calling `mmap.mmap` on Windows apparently resets the file offset of the raw file object (and makes the BufferedReader return a *negative* file offset). For safetensors, avoid using the file offset after calling mmap. For GGML format, explicitly save and restore the offset. Fixes #966.
2023-04-15Fix potential int8 overflow in non-SIMD vec_dot (#986)Stephan Walter
2023-04-15Refactor ggml.c for future tensor types (#1001)Stephan Walter
2023-04-15ggml : add Q8_0 quantization for intermediate results (#951)Georgi Gerganov
* ggml : add Q8_0 quantization for intermediate results * quantize-stats : fix test + add it to Makefile default * Q8: use int8_t, AVX/AVX2 optimizations * ggml : fix quantize_row_q8_0() ARM_NEON rounding * minor : updates after rebase to latest master * quantize-stats : delete obsolete strings * ggml : fix q4_1 dot func --------- Co-authored-by: Stephan Walter <stephan@walter.name>
2023-04-15ggml : use posix_memalign on non-Windows envGeorgi Gerganov
2023-04-15benchmark : fix result validation in benchmark-q4_0-matmult (#987)Ivan Komarov
2023-04-15cmake : add finding the OpenBLAS header file (#992)katsu560
2023-04-14Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982)Pavol Rusnak
This reverts commit f4d277ae17247ee51129ef1a9ff74d377cc90b1b.
2023-04-14py : bump sentencepiece to 0.1.98 to support Python 3.11 (#976)Pavol Rusnak
2023-04-14make : fix dependencies, use auto variables (#983)Stephan Walter
2023-04-14Expose type name from ggml (#970)Pavol Rusnak
Avoid duplication of type names in utils Co-authored-by: Håkon H. Hitland <haakon@likedan.net>
2023-04-14main : alternative instruct mode (Vicuna support, etc.) (#863)Tomáš Pazdiora
* Add support for configs, add configurable prefixes / suffixes, deprecate instruct mode, add stop prompt * Add multiline mode, update text input. * bugfix * update implementation * typos * Change --multiline implementation to be toggled by EOF. * bugfix * default multiline mode * add more configs * update formating * update formatting * apply suggestions
2023-04-14ggml : add unary and binary map operations (#874)Kerfuffle
* GGML map ops proof of concept. * Various cleanups. Add handling for task setting. Add handling for ggml_compute_backward. Rename functions to ggml_map_unary_f32 and ggml_map_binary_f32 Fix compiler warnings related to casting function pointers and `void *` Reorder functions and definitions based on the GGML op number. Use typedefs for map op function pointer types. * Fix position of map ops cases in ggml_compute_forward
2023-04-14py : cleanup dependencies (#962)Pavol Rusnak
after #545 we do not need torch, tqdm and requests in the dependencies
2023-04-14py : fix flake8 and isort nitpicks (#960)Pavol Rusnak
2023-04-14ggml : minorGeorgi Gerganov
2023-04-14ggml : always allocate buffers with size multiple of GGML_MEM_ALIGNGeorgi Gerganov
2023-04-14py : new conversion script (#545)comex
Current status: Working, except for the latest GPTQ-for-LLaMa format that includes `g_idx`. This turns out to require changes to GGML, so for now it only works if you use the `--outtype` option to dequantize it back to f16 (which is pointless except for debugging). I also included some cleanup for the C++ code. This script is meant to replace all the existing conversion scripts (including the ones that convert from older GGML formats), while also adding support for some new formats. Specifically, I've tested with: - [x] `LLaMA` (original) - [x] `llama-65b-4bit` - [x] `alpaca-native` - [x] `alpaca-native-4bit` - [x] LLaMA converted to 'transformers' format using `convert_llama_weights_to_hf.py` - [x] `alpaca-native` quantized with `--true-sequential --act-order --groupsize 128` (dequantized only) - [x] same as above plus `--save_safetensors` - [x] GPT4All - [x] stock unversioned ggml - [x] ggmh There's enough overlap in the logic needed to handle these different cases that it seemed best to move to a single script. I haven't tried this with Alpaca-LoRA because I don't know where to find it. Useful features: - Uses multiple threads for a speedup in some cases (though the Python GIL limits the gain, and sometimes it's disk-bound anyway). - Combines split models into a single file (both the intra-tensor split of the original and the inter-tensor split of 'transformers' format files). Single files are more convenient to work with and more friendly to future changes to use memory mapping on the C++ side. To accomplish this without increasing memory requirements, it has some custom loading code which avoids loading whole input files into memory at once. - Because of the custom loading code, it no longer depends in PyTorch, which might make installing dependencies slightly easier or faster... although it still depends on NumPy and sentencepiece, so I don't know if there's any meaningful difference. In any case, I also added a requirements.txt file to lock the dependency versions in case of any future breaking changes. - Type annotations checked with mypy. - Some attempts to be extra user-friendly: - The script tries to be forgiving with arguments, e.g. you can specify either the model file itself or the directory containing it. - The script doesn't depend on config.json / params.json, just in case the user downloaded files individually and doesn't have those handy. But you still need tokenizer.model and, for Alpaca, added_tokens.json. - The script tries to give a helpful error message if added_tokens.json is missing.
2023-04-14ggml : fix q4_1 dot product typesGeorgi Gerganov
2023-04-14ggml : optimize rope function to avoid call powf in the tight loop (#807)Howard Su
2023-04-14perplexity : add support for batch size to `--perplexity` (#407)Gary Linscott
* Add support to batch size for perplexity * Revert "Fix memory allocation issues and seg faults" This reverts commit 4870e455b3653f7d7769fa5772b2c90ffad088df. * update from merge * Remove perplexity from main * updates * Update batch size for efficiency
2023-04-13common : remove unnecessary includes (#947)CRD716
2023-04-13ggml : add GGML_DEFAULT_N_THREADSGeorgi Gerganov
2023-04-13ggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit ARM support (#900)Georgi Gerganov
* ggml : speed-up q4_1 ARM_NEON by ~5% * ggml : implement vaddvq when missing * ggml : implement vminvq and vmaxvq when missing * ggml : implement vzip when missing * ggml : fix comment * ggml : try to use correct ifdef
2023-04-13llama : merge llama_internal.h into llama.hGeorgi Gerganov
Hide it behind an #ifdef
2023-04-13gitignore : benchmarkGeorgi Gerganov
2023-04-13ggml : optimize non-SIMD Q4_0 vector dot product (#703)Stephan Walter
2023-04-13ggml : introduce GGML_ALIGNED_MALLOC/GGML_ALIGNED_FREE macros (#884)Pavol Rusnak
which allows us to use aligned_alloc or _aligned_malloc functions
2023-04-13fix whitespace (#944)CRD716
2023-04-13readme : remove python 3.10 warning (#929)CRD716
2023-04-13readme : llama node binding (#911)Genkagaku.GPT
* chore: add nodejs binding * chore: add nodejs binding