summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-09-04ggml-opencl : store GPU buffer in ggml_tensor::extra (#2994)slaren
2023-09-04llama-bench : make cpp file non-executable (#2999)Cebtenzzre
2023-09-04make : add speculative example (#3003)Leng Yue
2023-09-04server : add a subtle loading animation to the edit box (#2466)Aarni Koskela
* editorconfig: add override for the server HTML (which already is 2-space indented) * server: add a subtle loading animation to the edit box
2023-09-042x faster (rms) norm cuda kernels (3.7% e2e improvement) (#2985)Jiahao Li
* 2x faster (rms) norm cuda kernels * Fix code style
2023-09-03ggml-alloc : use virtual memory for measurement (#2973)slaren
* ggml-alloc : use virtual memory for measurement * compatibility fixes for MAP_ANONYMOUS * fallback to fixed address for systems without virtual memory
2023-09-03speculative : PoC for speeding-up inference via speculative sampling (#2926)Georgi Gerganov
* speculative : initial example * speculative : print encoding speed * speculative : add --draft CLI arg
2023-09-03perplexity : fix ETA by warming up the model with an empty runGeorgi Gerganov
2023-09-03gguf(python): Fix special vocab handling when id < 0 (#2984)Kerfuffle
2023-09-03metal : restore 363f0bf and fix reduce in F16_F32 kernels (#2986)Georgi Gerganov
2023-09-03cov : disable comment in PRs (#2989)Alon
2023-09-03llama : fix bpe tokenize from byte (#2889)opparco
2023-09-03metal : revert 6af0bab until we fix itGeorgi Gerganov
This restores the generated text to be the same as before #2959
2023-09-03cov : add Code Coverage and codecov.io integration (#2928)Alon
* update .gitignore * makefile: add coverage support (lcov, gcovr) * add code-coverage workflow * update code coverage workflow * wun on ubuntu 20.04 * use gcc-8 * check why the job hang * add env vars * add LLAMA_CODE_COVERAGE=1 again * - add CODECOV_TOKEN - add missing make lcov-report * install lcov * update make file -pb flag * remove unused GGML_NITER from workflows * wrap coverage output files in COV_TARGETS
2023-09-03opencl : fix a bug in ggml_cl_pool_malloc() for ggml_cl_mul_mat_f32() (#2955)Wentai Zhang
Co-authored-by: Wentai Zhang <wentaizhang@tencent.com>
2023-09-03metal : more optimizations (#2959)Kawrakow
* Very minor speedup via simd-group synchronization in f16 x f32 * Another very minor speedup on metal * Quite significant PP speedup on metal * Another attempt * Minor * Massive improvement for TG for fp16 * ~4-5% improvement for Q8_0 TG on metal --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-09-03swift : add support for k-quants (#2983)kchro3
2023-09-03convert.py : BPE fixes (#2938)Kerfuffle
* convert.py: BPE fixes? * Remove unnecessary conditional in addl token error handling
2023-09-03docs : add `catai` to `README.md` (#2967)Ido S
2023-09-03examples : fix gpt-neox (#2943)momonga
Co-authored-by: mmnga <mmnga1mmnga@gmail.com>
2023-09-03swift : add missing c file to Package.swift (#2978)kchro3
2023-09-03make : support overriding CFLAGS/CXXFLAGS/CPPFLAGS/LDFLAGS (#2886)Cebtenzzre
* make : remove unused -DGGML_BIG_ENDIAN * make : put preprocessor stuff in CPPFLAGS * make : pass Raspberry Pi arch flags to g++ as well * make : support overriding CFLAGS/CXXFLAGS/CPPFLAGS/LDFLAGS * make : fix inverted conditional
2023-09-02logging: Fix creating empty file even when disabled (#2966)Kerfuffle
* logging: Fix creating empty file even when disabled * Minor formatting fix Co-authored-by: staviq <staviq@gmail.com> --------- Co-authored-by: staviq <staviq@gmail.com>
2023-09-02readme : update clblast instructions (#2903)bandoti
* Update Windows CLBlast instructions * Update Windows CLBlast instructions * Remove trailing whitespace
2023-09-02metal : show all Metal device instances in the system (#2952)Karsten Weiss
* ggml_metal_init: Show all Metal device instances in the system Also show the default Metal device that was picked. * Update ggml-metal.m --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-09-02k-quants : fix build on armv7 (android only) (#2920)Jhen-Jie Hong
* k-quants : fix build on armv7 * ggml : cleanup unused arm32 specific impl * k-quants : avoid some unused vzero / mzero define * ggml-alloc : use 4g for MEASURE_MAX_SIZE in 32-bit arm
2023-09-02server : avoid aniprompt in probabilities of final response (#2849)Jhen-Jie Hong
2023-09-01cuda : vsubss4 for older versions of ROCm/clang (#2942)Engininja2
2023-09-01readme : quick start command fix (#2908)ZHAOKAI WANG
* quick start command fix * quick start win command fix
2023-09-01Allow quantize to only copy tensors, some other improvements (#2931)Kerfuffle
* Allow quantize tool to only copy tensors to allow repackaging models. * Slightly better logic when requantizing. * Change help message to go to `stdout`.
2023-09-01llama2c : rename functionGeorgi Gerganov
2023-09-01make : use unaligned vector moves on MinGW (#2945)Cebtenzzre
Fixes #2922
2023-09-01minor : add const qualifiers (#2853)m3ndax
* made the methods const # Conflicts: # examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp * made method const * Update convert-llama2c-to-ggml.cpp removed write_raw and write_u32 * llama2c : remove misleading const --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-09-01docs : add java-llama.cpp to README.md (#2935)Konstantin Herud
2023-09-01build : fix most gcc and clang warnings (#2861)Cebtenzzre
* fix most gcc and clang warnings * baby-llama : remove commented opt_params_adam * fix some MinGW warnings * fix more MinGW warnings
2023-09-01examples : add C grammar (#2357)Ben Siraphob
2023-09-01ggml : add RISC-V vector intrinsics support (#2929)Tameem
* added support for RISCV CFLAGS & native compile + cross compile options * Add RISC-V Vector Intrinsics Support Added RVV intrinsics for following ggml_vec_dot_q4_0_q8_0 ggml_vec_dot_q4_1_q8_1 ggml_vec_dot_q5_0_q8_0 ggml_vec_dot_q5_1_q8_1 ggml_vec_dot_q8_0_q8_0 Co-authored-by: Sharafat <sharafat.hussain@10xengineers.ai> Signed-off-by: Ahmad Tameem <ahmad.tameem@10xengineers.ai> --------- Signed-off-by: Ahmad Tameem <ahmad.tameem@10xengineers.ai> Co-authored-by: moiz.hussain <moiz.hussain@10xengineers.ai> Co-authored-by: Sharafat <sharafat.hussain@10xengineers.ai>
2023-09-01metal : slight speed-up for add and mul kernels (#2917)Georgi Gerganov
2023-09-01logs : fix mingw-like builds (fixes #2898) (#2911)staviq
* fix mingw-like builds * formatting * make LOG_COMPAT easier to override and extend * simplify win detection * fix for #2940
2023-09-01llama2c : fix segfault and alloc-dealloc-mismatch (#2913)Cebtenzzre
* llama2c : fix segfault if vocab is not found * llama2c : fix mismatch between new[] and delete * llama2c : fix basename on Windows * llama2c : use a destructor to prevent memory leaks
2023-09-01metal: somewhat faster f16 x f32 matrix multiply kernel (#2951)Kawrakow
* Somewhat faster f16 x f32 matrix multiply kernel * Better use 32 thread groups for f16 x f32 --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-08-31convert : fix another python 3.8 issue (#2949)Cebtenzzre
2023-09-01remove convert-llama-7b-pth-to-gguf.py and convert-llama-hf-to-gguf.py (#2906)slaren
2023-08-31scripts: Use local gguf package when running from repo (#2927)Kerfuffle
* scripts: Use local gguf when running from repo
2023-08-31@vxiiduu's fix for PrefetchVirtualMemory (#2930)DannyDaemonic
Reimplement fix for `PrefetchVirtualMemory`. Co-authored-by: vxiiduu <73044267+vxiiduu@users.noreply.github.com>
2023-08-31convert : fix python 3.8 support, modernize type annotations (#2916)Cebtenzzre
* convert : fix python 3.8 support * convert : sort imports * convert : fix required parameters in convert-llama-ggmlv3-to-gguf * convert : fix mypy errors in convert-llama-ggmlv3-to-gguf * convert : use PEP 585 generics and PEP 604 unions Now that we have `from __future__ import annotations`, we can use this modern syntax in Python 3.7 instead of restricting support to Python 3.9 or 3.10 respectively. * gguf.py : a tuple is already a tuple * add mypy.ini * convert : add necessary `type: ignore` comments * gguf-py: bump version
2023-08-30CUDA: mul_mat_q=true llama_context_params default (#2912)Johannes Gäßler
2023-08-30[Docker] fix tools.sh argument passing. (#2884)Henri Vasserman
* [Docker] fix tools.sh argument passing. This should allow passing multiple arguments to containers with the full image that are using the tools.sh frontend. Fix from https://github.com/ggerganov/llama.cpp/issues/2535#issuecomment-1697091734
2023-08-30convert.py : use dir name to name the llamaGeorgi Gerganov
2023-08-30examples : fix underscore in beam-search + .gitignore (close #2900)Georgi Gerganov
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-18 19:36:46 +0000