aboutsummaryrefslogtreecommitdiff
path: root/examples/common.cpp
AgeCommit message (Collapse)Author
2023-07-11llama : add classifier-free guidance (#2135)Bach Le
* Initial implementation * Remove debug print * Restore signature of llama_init_from_gpt_params * Free guidance context * Make freeing of guidance_ctx conditional * Make Classifier-Free Guidance a sampling function * Correct typo. CFG already means context-free grammar. * Record sampling time in llama_sample_classifier_free_guidance * Shift all values by the max value before applying logsoftmax * Fix styling based on review
2023-07-11Support using mmap when applying LoRA (#2095)Howard Su
* Support using mmap when applying LoRA * Fix Linux * Update comment to reflect the support lora with mmap
2023-07-09main : escape prompt prefix/suffix (#2151)Nigel Bosch
2023-06-29Use unsigned for random seed (#2006)Howard Su
* Use unsigned for random seed. Keep -1 as the value to use a time based seed. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-28CUDA GPU acceleration for LoRAs + f16 models (#1970)Johannes Gäßler
2023-06-26ggml : add NUMA support (#1556)zrm
* detect NUMA systems and pin work threads to nodes (linux) * disable mmap prefetch/readahead for NUMA systems * avoid sending finalize op to thread pool if it does nothing * silence robot * fix args * make --numa a param * recommendation that n_nodes evenly divide n_threads did not warrant such aggressive enforcement * lower synchronization overhead * statically allocate * move numa state to g_state * add description for --numa * ggml : minor style changes * ggml : minor style + try fix sanitizer build * llama : allow to initialize backend with NUMA support * llama : avoid ggml include in llama-util.h * ggml : style / formatting * ggml : fix handling of ops with n_threads > n_tasks > 1 * server : utilize numa parameter --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-24llama : make model stateless and context stateful (llama_state) (#1797)Didzis Gosko
* llama : make model stateless and context stateful * llama : minor cleanup * llama : update internal API declaration * Apply suggestions from code review fix style Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Missing model memory release * Fix style * Add deprecated warning for public API function llama_init_from_file * Update public API use cases: move away from deprecated llama_init_from_file * Deprecate public API function llama_apply_lora_from_file --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-17Only one CUDA stream per device for async compute (#1898)Johannes Gäßler
2023-06-16build : fix and ignore MSVC warnings (#1889)Borislav Stanimirov
2023-06-15Better error when using both LoRA + GPU layers (#1861)Johannes Gäßler
2023-06-14CUDA full GPU acceleration, KV cache in VRAM (#1827)Johannes Gäßler
* Fixed CUDA RoPE * ggml_cuda_mul_mat_vec_p021 * ggml_cuda_scale * ggml_cuda_diag_mask_inf * ggml_is_permuted * ggml_cuda_cpy * flatten rows for ggml_cuda_op * Added a --low-vram option * Fixed Windows performance * Fixed LLAMA_CUDA_DMMV_Y > 1 for WizardLM
2023-06-11Fix issue where interactive mode crashes when input exceeds ctx size (#1789)Kerfuffle
* Fix issue where interactive mode in the main example crashes when input exceeds ctx size * Ensure the context size is at least 8 tokens in the main example. Closes #1768
2023-06-06main: add the possibility to open the prompt cache read-only (#1640)Willy Tarreau
The prompt cache constitutes a nice speed up when using the same prompt prefix across multiple evaluations, but when using it, it will also be updated, which is not always desirable. One use case is to have a large prompt containing some context and usage rules, and a second part containing variable data of the problem being studied. In this case it's desirable to be able to save the first part once, and to always reuse it as-is without updating it with the second part. The new argument --prompt-cache-ro enables this read-only mode on the prompt cache. The prompt's contents that match the cache are loaded from the cache but the rest is not modified. This allowed to reduce a total analysis time from 112s to 49.7s here, without having to backup and restore a copy of the prompt, which takes significant time at 500 MB. Signed-off-by: Willy Tarreau <w@1wt.eu>
2023-06-06Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)Johannes Gäßler
* CUDA multi GPU + scratch ggml_cuda_compute_forward Tensor parallelism ggml_cuda_add ggml_cuda_rms_norm ggml_cuda_silu CUDA scratch buffer --main-gpu CLI option
2023-06-04llama : Metal inference (#1642)Georgi Gerganov
* mtl : export the LLaMA computation graph * ci : disable temporary * mtl : adapt the MNIST example as starter * mtl : no need for mtl-export tool, add cli arg for main instead * mtl : export just a small part of the graph for now to make it easier * mtl : move MSL code into separate file for easy editing * mtl : initial get_rows_q4_0 kernel * mtl : confirmed get_rows_q4_0 is working correctly * mtl : add rms_norm kernel + confirm working * mtl : add mul kernel + confirm working * mtl : initial mul_mat Q4 kernel (wrong results) * mtl : mul_mat fixes (still wrong) * mtl : another mul_mat Q4 (still does not work) * mtl : working mul_mat q4 * ggml : fix handling of "view" ops in ggml_graph_import() * mtl : add rope kernel * mtl : add reshape and transpose handling * ggml : store offset as opt arg for ggml_view_xd() operators * mtl : add cpy kernel + handle view ops * mtl : confirm f16 x f32 attention mul mat * mtl : add scale kernel * mtl : add diag_mask_inf kernel * mtl : fix soft_max kernel * ggml : update ggml_nbytes() to handle non-contiguous tensors * mtl : verify V tensor contents * mtl : add f32 -> f32 cpy kernel * mtl : add silu kernel * mtl : add non-broadcast mul kernel * mtl : full GPU inference of the computation graph * mtl : optimize rms_norm and soft_max kernels * mtl : add f16 mat x f32 vec multiplication kernel * mtl : fix bug in f16 x f32 mul mat + speed-up computation * mtl : faster mul_mat_q4_0_f32 kernel * mtl : fix kernel signature + roll inner loop * mtl : more threads for rms_norm + better timing * mtl : remove printfs from inner loop * mtl : simplify implementation * mtl : add save/load vocab to ggml file * mtl : plug Metal inference into llama.cpp (very quick-n-dirty) * mtl : make it work with main example Lots of hacks but at least now it generates text * mtl : preparing for merge * mtl : clean-up ggml mtl interface + suport scratch / inplace * mtl : remove temp / debug code * metal : final refactoring and simplification * Revert "ci : disable temporary" This reverts commit 98c267fc77fe811082f672538fc91bcfc9072d63. * metal : add comments * metal : clean-up stuff, fix typos * readme : add Metal instructions * readme : add example for main
2023-05-28Only show -ngl option when relevant + other doc/arg handling updates (#1625)Kerfuffle
1. Add a `LLAMA_SUPPORTS_GPU_OFFLOAD` define to `llama.h` (defined when compiled with CLBlast or cuBLAS) 2. Update the argument handling in the common example code to only show the `-ngl`, `--n-gpu-layers` option when GPU offload is possible. 3. Add an entry for the `-ngl`, `--n-gpu-layers` option to the `main` and `server` examples documentation 4. Update `main` and `server` examples documentation to use the new style dash separator argument format 5. Update the `server` example to use dash separators for its arguments and adds `-ngl` to `--help` (only shown when compiled with appropriate support). It will still support `--memory_f32` and `--ctx_size` for compatibility. 6. Add a warning discouraging use of `--memory-f32` for the `main` and `server` examples `--help` text as well as documentation. Rationale: https://github.com/ggerganov/llama.cpp/discussions/1593#discussioncomment-6004356
2023-05-28examples : add --alias option to gpt_params to set use friendly model name ↵Vladimir Zorin
(#1614)
2023-05-20Fix for mingw (#1462)DannyDaemonic
2023-05-19main : make reverse prompt option act as a stop token in non-interactive ↵Jason McCartney
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
2023-05-19minor : fix compile warningsGeorgi Gerganov
2023-05-17Remove unused n_parts parameter (#1509)Stephan Walter
2023-05-15fix get_num_physical_cores() (#1436)zrm
* fix get_num_physical_cores() had been broken on complex topologies because "cpu cores" in /proc/cpuinfo is per-"physical id" * Add spaces to maintain consistent formatting --------- Co-authored-by: slaren <ddevesa@gmail.com>
2023-05-13ggml : GPU-accelerated token generation (#1412)Johannes Gäßler
* CUDA kernel for q4_0 dequant. + mat. vec. mult. * Added q4_1 via template * Added missing __syncthreads(); * --gpu_layers -> --gpu-layers * Shorter dequantize_mul_mat_vec line * q5_0 dequantize_mul_mat kernel * More readable dequantize_mul_mat_vec logic * dequantize_mul_mat_vec kernels for q5_1, q8_0, f16 * llama : offload "output" tensor to GPU too + coding style fixes --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-05-12CLI args use - instead of _, backwards compatible (#1416)Johannes Gäßler
2023-05-10main : add option to save full output to session (#1338)Evan Jones
* main : add option to save full output to session * split behavior into --session and --prompt-cache * restore original implementation with new names * PR comments * move the check for incompatible parameters to gpt_params_parse * Fix whitespace Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com> --------- Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com>
2023-05-09Locale fix for Windows (#1379)DannyDaemonic
2023-05-08Interface improvements and `--multiline-input` (previously `--author-mode`) ↵DannyDaemonic
(#1040) * Interface improvements * Multiline input * Track character width * Works with all characters and control codes + Windows console fixes
2023-05-08llama : require first token to be BOS (#1303)Georgi Gerganov
* llama : require first token to be BOS * scripts : add ppl-run-all.sh * perplexity : add BOS for each chunk * readme : update perplexity values after BOS fix * perplexity : add clarifying comments
2023-05-08Documented CUDA reproducibility, added warning (#1346)Johannes Gäßler
2023-05-04main : add --in-suffix option (#1318)44670
* adding --in-suffix option * print input suffix before generation
2023-05-04Only escape prompts when used with `-e` (#1311)DannyDaemonic
2023-05-02Process escape sequences given in prompts (#1173)DannyDaemonic
2023-05-03fix missing parameters in `llama_init_from_gpt_params` (#1293)slaren
2023-05-02examples : add llama_init_from_gpt_params() common function (#1290)Ron Evans
Signed-off-by: deadprogram <ron@hybridgroup.com>
2023-05-02llama : allow 0 as a seed number. (#1275)Robert Brisita
2023-04-30common : better default number of threads (#934)jon-chuang
* commit * fix * try-catch * apply code review * improve * improve * add macos headers * done * remove color * fix windows * minor * fix * Apply suggestions from code review Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com> * remove * minor * minor --------- Co-authored-by: jon-chuang <jon-chuang@users.noreply.github.com> Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com>
2023-04-29llama : new sampling algorithms (#1126)Ivan Stepanov
* Sample interface, new samplers. New samplers: - locally typical sampling - tail free sampling - frequency and presence penalty - mirostat Ignore EOS fix: -inf should be used. * mirostat * Added --logit-bias and --no-penalize-nl, removed std::span * Use C++11, clarify llama API documentation, rename Mirostat parameters to --mirostat_lr and --mirostat_ent, add temperature sampling for Mirostat, simplify Mirostat sampling API parameters (removed N and *k) Use C++11, clarify llama API documentation, rename Mirostat parameters to --mirostat_lr and --mirostat_ent, add temperature sampling for Mirostat, simplify Mirostat sampling API parameters (removed N and *k) * Save and load example adjust * Tests * Windows build fix * Windows test fix
2023-04-28llama : add session file format and saved sessions in main (#1169)Evan Jones
2023-04-24examples/main README improvements and some light refactoring (#1131)mgroeber9110
2023-04-17Add LoRA support (#820)slaren
2023-04-14Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982)Pavol Rusnak
This reverts commit f4d277ae17247ee51129ef1a9ff74d377cc90b1b.
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
2023-04-13common : remove unnecessary includes (#947)CRD716
2023-04-11Fix whitespace, add .editorconfig, add GitHub workflow (#883)Pavol Rusnak
2023-04-10Rewrite loading code to try to satisfy everyone:comex
- Support all three formats (ggml, ggmf, ggjt). (However, I didn't include the hack needed to support GPT4All files without conversion. Those can still be used after converting them with convert.py from my other PR.) - Support both mmap and read (mmap is used by default, but can be disabled with `--no-mmap`, and is automatically disabled for pre-ggjt files or on platforms where mmap is not supported). - Support multi-file models like before, but automatically determine the number of parts rather than requiring `--n_parts`. - Improve validation and error checking. - Stop using the per-file type field (f16) entirely in favor of just relying on the per-tensor type/size fields. This has no immediate benefit, but makes it easier to experiment with different formats, and should make it easier to support the new GPTQ-for-LLaMa models in the future (I have some work in progress on that front). - Support VirtualLock on Windows (using the same `--mlock` option as on Unix). - Indicate loading progress when using mmap + mlock. (Which led me to the interesting observation that on my Linux machine, with a warm file cache, mlock actually takes some time, whereas mmap without mlock starts almost instantly...) - To help implement this, move mlock support from ggml to the loading code. - madvise/PrefetchVirtualMemory support (based on #740) - Switch from ifstream to the `fopen` family of functions to avoid unnecessary copying and, when mmap is enabled, allow reusing the same file descriptor for both metadata reads and mmap (whereas the existing implementation opens the file a second time to mmap). - Quantization now produces a single-file output even with multi-file inputs (not really a feature as much as 'it was easier this way'). Implementation notes: I tried to factor the code into more discrete pieces than before. Regarding code style: I tried to follow the code style, but I'm naughty and used a few advanced C++ features repeatedly: - Destructors to make it easier to ensure everything gets cleaned up. - Exceptions. I don't even usually use exceptions when writing C++, and I can remove them if desired... but here they make the loading code much more succinct while still properly handling a variety of errors, ranging from API calls failing to integer overflow and allocation failure. The exceptions are converted to error codes at the API boundary.) Co-authored-by: Pavol Rusnak <pavol@rusnak.io> (for the bit I copied from #740)
2023-04-08fix for windows utf-8 input (#840)Tomáš Pazdiora
Use UTF-16 as input on Windows, since UTF-8 does not work and reads multibyte characters as zeros
2023-04-02fix default params for examples/main (#697)Murilo Santana
2023-04-01Show error message when -f failsSlaren
2023-03-28all : be more strict about converting float to double (#458)Stephan Walter
* Be more strict about converting float to double * Test equivalence of round, SILU implementations Test module is commented out in CMakeLists.txt because the tests may take a long time, depending on how much the compiler optimizes. * Fix softmax in perplexity.cpp * all : prefer float over double where appropriate * perplexity : add <cmath> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-28main.cpp fixes, refactoring (#571)anzz1
- main: entering empty line passes back control without new input in interactive/instruct modes - instruct mode: keep prompt fix - instruct mode: duplicate instruct prompt fix - refactor: move common console code from main->common