summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-08-14CUDA: launch_bounds, small q4_K, q5_K mmq refactor (#2596)Johannes Gäßler
2023-08-14server : fix default grammar by use empty string in the UI (#2604)Jhen-Jie Hong
2023-08-14server : implement json-schema-to-grammar.mjs & add grammar param in the UI ↵Jhen-Jie Hong
(#2588) * server : implement json-schema-to-grammar.mjs by follow python impl * server : add grammar support in chat.mjs * server : implement grammer param in the UI * server : generate .hpp * server : remove trailing whitespaces * server : generate .hpp * server : fix sort of prop pairs * server : optimize regex & iteration
2023-08-13Enhance Windows 7 and below compatibility. (#2592)vxiiduu
* Enhance Windows 7 compatibility. * Clean away unnecessary preprocessor conditional
2023-08-13test : add simple grammar parsing tests (#2594)drbh
* adds simple grammar parsing tests * adds cassert header
2023-08-13CUDA: Fixed OpenLLaMA 3b mmq, reduced compile time (#2590)Johannes Gäßler
2023-08-12Adding support for llama2.c models (#2559)byte-6174
2023-08-12server: fixed wrong variable name in timing json (#2579)Equim
* server: fixed wrong variable name in timing json * remove redunct entry
2023-08-10Handle `ENABLE_VIRTUAL_TERMINAL_PROCESSING` more gracefully on earlier ↵DannyDaemonic
versions of Windows.
2023-08-10Add --n-predict -2 for stopping generation on full context (#2565)Christian Demsar
2023-08-10Fix grammar-based sampling issue in server (#2566)Martin Krasser
2023-08-09ggml-alloc: Don't try to re-use buffers of external tensors (#2562)Sam Spilsbury
* ggml-alloc: Don't try to re-use buffers of external tensors They might be weights that came from another context, so we have no control over them (and they might be re-used elsewhere so writing to them would be a bad idea). * ggml-alloc: >= when checking for out-of-bounds Co-authored-by: slaren <slarengh@gmail.com> --------- Co-authored-by: slaren <slarengh@gmail.com>
2023-08-09add log_callback to llama_context_params for custom logging. (#2234)grahameth
* add log_callback to llama_context_params for custom logging. * Fix macro expansion on gcc * Add struct llama_state for global variables and move log_callback there * Turn log level into enum and some minor changes. * Remove model_for_logging parameter (not needed anymore) * Convert remaining fprintf(stderr, ...) calls to use new macros. * Fix enum and initialize g_state * Fix log calls after merge * Fix missing static * Add back all the new lines in the logging strings * Add comment for llama_log_callback and replace remaining printf calls --------- Co-authored-by: grahameth <-> Co-authored-by: Helmut <helmut.buhler@inf.h-brs.de>
2023-08-09CUDA: tuned mul_mat_q kernels (#2546)Johannes Gäßler
2023-08-08Allow passing grammar to completion endpoint (#2532)Martin Krasser
* Allow passing grammar to completion endpoint
2023-08-08CUDA: tighter VRAM scratch size for 65b/70b (#2551)Johannes Gäßler
2023-08-08llm.vim : multiline autocompletion, get rid of "^@" (#2543)chaihahaha
2023-08-08vim : bring back simple llm.vim exampleGeorgi Gerganov
2023-08-08vim : streaming and more (#2495)AustinMroz
* Update Vim plugin * Remove getbufoneline usage, Add input bind example. getbufoneline() appears to be a recently added function and has been replaced with getbufline for compatibility. An additional example that explains how to add a keybind that works in insert mode was added.
2023-08-07Add --rope-scale parameter (#2544)klosax
* common.cpp : Add --rope-scale parameter * README.md : Add info about using linear rope scaling
2023-08-07ggml : mul mat tweaks (#2372)Georgi Gerganov
* ggml : mul mat wip ggml-ci * ggml : alternative thread distribution for mul_mat ggml-ci * ggml : mul_mat block tiling attempt * ggml : mul_mat threads yield ggml-ci
2023-08-07ggml : pad result of ggml_nbytes()Georgi Gerganov
2023-08-07ggml : change params pointer (style change) (#2539)Georgi Gerganov
ggml-ci
2023-08-07ggml : sync (custom ops) (#2537)Georgi Gerganov
ggml-ci
2023-08-07Fixed mmap prefetch for GPU offloading (#2529)Johannes Gäßler
2023-08-07metal : fix out-of-bounds access + inc concurrency nodes (#2416)Georgi Gerganov
* metal : fix out-of-bounds access + style changes * metal : increase concurrency nodes to 2*GGML_MAX_NODES
2023-08-07[Makefile] Move ARM CFLAGS before compilation (#2536)GiviMAD
2023-08-07[Zig] Rewrite build for Zig 0.11 (#2514)Henri Vasserman
* zig build fixes * Disable LTO on Windows.
2023-08-06console : fix issue related to Windows 11 PowerShell console mode ↵DannyDaemonic
persistence (#2521)
2023-08-06convert.py : add missing abstract methods for quantized data (#2491)Keiichi Tabata
2023-08-05CUDA: faster k-quant mul_mat_q kernels (#2525)Johannes Gäßler
2023-08-04fix firefox autoscroll (#2519)Jonas Wunderlich
2023-08-04server: regenerate completion.js.hpp (#2515)Cebtenzzre
2023-08-04CUDA: use min compute capability of GPUs actually used (#2506)Cebtenzzre
2023-08-04CUDA: check if event is NULL before cudaStreamWaitEvent (#2505)Cebtenzzre
Fixes #2503
2023-08-04Add --simple-io option for subprocesses and break out console.h and cpp (#1558)DannyDaemonic
2023-08-04Fixing race condition in server and partial stream handling in frontend. (#2391)Stephen Nichols
* Fixing race condition in server.cpp and partial stream handling in completion.js * Reverting assert edits. * Adding newline to eof
2023-08-04Stream save llama context data to file instead of allocating entire buffer ↵l3utterfly
upfront (#2488) * added stream saving context data to file to avoid allocating unnecessary amounts of memory * generalised copying state data to file or buffer * added comments explaining how copy_state_data works * fixed trailing whitespaces * fixed save load state example * updated save load state to use public function in llama.cpp * - restored breakage of the llama_copy_state_data API - moved new logic for copying llama state data to internal function * fixed function declaration order * restored save load state example * fixed whitepace * removed unused llama-util.h include * Apply suggestions from code review Co-authored-by: slaren <slarengh@gmail.com> * Apply code review suggestions Co-authored-by: slaren <slarengh@gmail.com> --------- Co-authored-by: slaren <slarengh@gmail.com>
2023-08-04build : fix several cast and printf warnings (#2499)Borislav Stanimirov
2023-08-02examples : generate JSON according to schema (#1887)Evan Jones
* examples : add JSON schema grammars * complete JSON grammar * ensure primitive types can be used as root of schema * support integer type and adjust usage text
2023-08-02CUDA: faster non k-quant mul_mat_q kernels (#2483)Johannes Gäßler
2023-08-02CUDA: Fix models with output size != 32000 (#2480)Johannes Gäßler
2023-08-02readme : add Aquila-7B model series to supported models (#2487)ldwang
* support bpe tokenizer in convert Signed-off-by: ldwang <ftgreat@gmail.com> * support bpe tokenizer in convert Signed-off-by: ldwang <ftgreat@gmail.com> * support bpe tokenizer in convert, fix Signed-off-by: ldwang <ftgreat@gmail.com> * Add Aquila-7B models in README.md Signed-off-by: ldwang <ftgreat@gmail.com> * Up Aquila-7B models in README.md Signed-off-by: ldwang <ftgreat@gmail.com> --------- Signed-off-by: ldwang <ftgreat@gmail.com> Co-authored-by: ldwang <ftgreat@gmail.com>
2023-08-02tests : Fix compilation warnings (Linux/GCC) (#2451)Eve
* fix hellaswag print format, cast away warning in test-double-float * c++11 cannot use designated initializers * add static to test-grad0.c internal functions * use memcpy in test-double-float.c * port c tests to c++ * use initializer list for ggml_init_params
2023-08-02readme : Add Chinese LLaMA-2 / Alpaca-2 to supported models (#2475)Yiming Cui
* add support for chinese llama-2 / alpaca-2 * remove white spaces
2023-08-01fix a typo in examples/server/README.md (#2478)Bono Lv
2023-08-01server : Support dark mode (#2414)ebraminio
* server : Support dark mode So it respects user system light / dark settings. * Update index.html.hpp by running ./deps.sh
2023-08-01metal : add gqa8 kernel to allow llama-2-70B on metal (#2459)Matteo Boschini
* Added gqa8 kernel to allow llama-2-70B on metal * Update ggml-metal.m Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com> * Extend kernel_mul_mat_f16_f32 to handle gqa broadcast * Added ne03==ne13 assertion --------- Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
2023-07-31CUDA: fixed LLAMA_FAST compilation option (#2473)Johannes Gäßler
2023-07-31CUDA: fixed cmake F16 option (#2471)Johannes Gäßler
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-19 07:53:08 +0000