root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 11:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
4d698495ea
llama.cpp/.gitignore

80 lines
877 B
Plaintext
Raw Normal View History

Initial release
2023-03-10 18:40:58 +00:00
*.o
*.a
llama : support input embeddings directly (#1910) * add interface for float input * fixed inpL shape and type * add examples of input floats * add test example for embd input * fixed sampling * add free for context * fixed add end condition for generating * add examples for llava.py * add READMD for llava.py * add READMD for llava.py * add example of PandaGPT * refactor the interface and fixed the styles * add cmake build for embd-input * add cmake build for embd-input * Add MiniGPT-4 example * change the order of the args of llama_eval_internal * fix ci error
2023-06-28 15:53:37 +00:00
*.so
ggml : use 8-bit precision for Q4_1 intermediate results (#1047) * ggml : use 8-bit precision for Q4_1 intermediate results (ARM) * ggml : optimize ggml_vec_dot_q4_1_q8_0() via vmalq_n_f32 56 ms/token with Q4_1 ! * ggml : AVX2 implementation of ggml_vec_dot_q4_1_q8_0 (#1051) * gitignore : ignore ppl-*.txt files --------- Co-authored-by: slaren <2141330+slaren@users.noreply.github.com>
2023-04-19 17:10:08 +00:00
.DS_Store
.build/
Initial release
2023-03-10 18:40:58 +00:00
.cache/
ggml : use 8-bit precision for Q4_1 intermediate results (#1047) * ggml : use 8-bit precision for Q4_1 intermediate results (ARM) * ggml : optimize ggml_vec_dot_q4_1_q8_0() via vmalq_n_f32 56 ms/token with Q4_1 ! * ggml : AVX2 implementation of ggml_vec_dot_q4_1_q8_0 (#1051) * gitignore : ignore ppl-*.txt files --------- Co-authored-by: slaren <2141330+slaren@users.noreply.github.com>
2023-04-19 17:10:08 +00:00
.direnv/
.envrc
.swiftpm
.venv
gitignore : add .clang-tidy
2023-06-06 06:55:10 +00:00
.clang-tidy
Initial release
2023-03-10 18:40:58 +00:00
.vs/
.vscode/
build/
build-em/
build-debug/
build-release/
ci : integrate with ggml-org/ci (#2250) * ci : run ctest ggml-ci * ci : add open llama 3B-v2 tests ggml-ci * ci : disable wget progress output ggml-ci * ci : add open llama 3B-v2 tg tests for q4 and q5 quantizations ggml-ci * tests : try to fix tail free sampling test ggml-ci * ci : add K-quants ggml-ci * ci : add short perplexity tests ggml-ci * ci : add README.md * ppl : add --chunks argument to limit max number of chunks ggml-ci * ci : update README
2023-07-18 11:24:43 +00:00
build-ci-debug/
build-ci-release/
Initial release
2023-03-10 18:40:58 +00:00
build-static/
ggml : add Q5_0 and Q5_1 quantization (#1187) * ggml : add Q5_0 quantization (cuBLAS only) * ggml : fix Q5_0 qh -> uint32_t * ggml : fix q5_0 histogram stats * ggml : q5_0 scalar dot product * ggml : q5_0 ARM NEON dot * ggml : q5_0 more efficient ARM NEON using uint64_t masks * ggml : rename Q5_0 -> Q5_1 * ggml : adding Q5_0 mode * quantize : add Q5_0 and Q5_1 to map * ggml : AVX2 optimizations for Q5_0, Q5_1 (#1195) --------- Co-authored-by: Stephan Walter <stephan@walter.name>
2023-04-26 20:14:13 +00:00
build-cublas/
llama : fix various warnings
2023-05-13 08:23:15 +00:00
build-opencl/
llama : Metal inference (#1642) * 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
2023-06-04 20:34:30 +00:00
build-metal/
mpi : add support for distributed inference via MPI (#2099) * MPI support, first cut * fix warnings, update README * fixes * wrap includes * PR comments * Update CMakeLists.txt * Add GH workflow, fix test * Add info to README * mpi : trying to move more MPI stuff into ggml-mpi (WIP) (#2099) * mpi : add names for layer inputs + prep ggml_mpi_graph_compute() * mpi : move all MPI logic into ggml-mpi Not tested yet * mpi : various fixes - communication now works but results are wrong * mpi : fix output tensor after MPI compute (still not working) * mpi : fix inference * mpi : minor * Add OpenMPI to GH action * [mpi] continue-on-error: true * mpi : fix after master merge * [mpi] Link MPI C++ libraries to fix OpenMPI * tests : fix new llama_backend API * [mpi] use MPI_INT32_T * mpi : factor out recv / send in functions and reuse * mpi : extend API to allow usage with outer backends (e.g. Metal) --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-10 15:49:56 +00:00
build-mpi/
Initial release
2023-03-10 18:40:58 +00:00
build-no-accel/
build-sanitize-addr/
build-sanitize-thread/
gitignore : add several entries specific to Visual Studio (#1888)
2023-06-16 06:58:11 +00:00
out/
ci : integrate with ggml-org/ci (#2250) * ci : run ctest ggml-ci * ci : add open llama 3B-v2 tests ggml-ci * ci : disable wget progress output ggml-ci * ci : add open llama 3B-v2 tg tests for q4 and q5 quantizations ggml-ci * tests : try to fix tail free sampling test ggml-ci * ci : add K-quants ggml-ci * ci : add short perplexity tests ggml-ci * ci : add README.md * ppl : add --chunks argument to limit max number of chunks ggml-ci * ci : update README
2023-07-18 11:24:43 +00:00
tmp/
Initial release
2023-03-10 18:40:58 +00:00
.gitignore models/
2023-03-11 10:26:46 +00:00
models/*
ci : integrate with ggml-org/ci (#2250) * ci : run ctest ggml-ci * ci : add open llama 3B-v2 tests ggml-ci * ci : disable wget progress output ggml-ci * ci : add open llama 3B-v2 tg tests for q4 and q5 quantizations ggml-ci * tests : try to fix tail free sampling test ggml-ci * ci : add K-quants ggml-ci * ci : add short perplexity tests ggml-ci * ci : add README.md * ppl : add --chunks argument to limit max number of chunks ggml-ci * ci : update README
2023-07-18 11:24:43 +00:00
models-mnt
.gitignore models/
2023-03-11 10:26:46 +00:00
Initial release
2023-03-10 18:40:58 +00:00
/main
/quantize
Add quantize-stats command for testing quantization (#728) Command that calculates some statistics over the errors introduced by quantization, like mean square error, max error and some percentile errors for layer weights. Should be useful for testing quantization improvements. Exposes some internal state from ggml and llama for testing
2023-04-07 22:09:18 +00:00
/quantize-stats
Nix flake (#40) * Nix flake * Nix: only add Accelerate framework on macOS * Nix: development shel, direnv and compatibility * Nix: use python packages supplied by withPackages * Nix: remove channel compatibility * Nix: fix ARM neon dotproduct on macOS --------- Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
2023-03-17 22:03:48 +00:00
/result
Overhaul the examples structure - main -> examples - utils -> examples (renamed to "common") - quantize -> examples - separate tools for "perplexity" and "embedding" Hope I didn't break something !
2023-03-25 18:26:40 +00:00
/perplexity
gitignore : add "embedding"
2023-03-28 15:34:35 +00:00
/embedding
make : add train-text-from-scratch (#1850) * make finetuning example accessible * fixed: targed was in wrong line * fixed: name of executable was wrong * fixed: naming of binary * fixed: model path was wrong * fixed clean target * Update examples/train-text-from-scratch/README.md --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-15 17:42:48 +00:00
/train-text-from-scratch
llama : fix kv_cache `n` init (close #1903)
2023-06-17 16:30:22 +00:00
/simple
Various fixes to mat_mul benchmark (#1253)
2023-04-30 12:32:37 +00:00
/benchmark-matmult
gitignore : vdot
2023-04-18 20:00:08 +00:00
/vdot
Server Example Refactor and Improvements (#1570) A major rewrite for the server example. Note that if you have built something on the previous server API, it will probably be incompatible. Check out the examples for how a typical chat app could work. This took a lot of effort, there are 24 PR's closed in the submitter's repo alone, over 160 commits and a lot of comments and testing. Summary of the changes: - adds missing generation parameters: tfs_z, typical_p, repeat_last_n, repeat_penalty, presence_penalty, frequency_penalty, mirostat, penalize_nl, seed, ignore_eos - applies missing top k sampler - removes interactive mode/terminal-like behavior, removes exclude parameter - moves threads and batch size to server command-line parameters - adds LoRA loading and matches command line parameters with main example - fixes stopping on EOS token and with the specified token amount with n_predict - adds server timeouts, host, and port settings - adds expanded generation complete response; adds generation settings, stop reason, prompt truncated, model used, and final text - sets defaults for unspecified parameters between requests - removes /next-token endpoint and as_loop parameter, adds stream parameter and server-sent events for streaming - adds CORS headers to responses - adds request logging, exception printing and optional verbose logging - adds better stopping words handling when matching multiple tokens and while streaming, or when it finishes on a partial stop string - adds printing an error when it can't bind to the host/port specified - fixes multi-byte character handling and replaces invalid UTF-8 characters on responses - prints timing and build info on startup - adds logit bias to request parameters - removes embedding mode - updates documentation; adds streaming Node.js and Bash examples - fixes code formatting - sets server threads to 1 since the current global state doesn't work well with simultaneous requests - adds truncation of the input prompt and better context reset - removes token limit from the input prompt - significantly simplified the logic and removed a lot of variables --------- Co-authored-by: anon998 <131767832+anon998@users.noreply.github.com> Co-authored-by: Henri Vasserman <henv@hot.ee> Co-authored-by: Felix Hellmann <privat@cirk2.de> Co-authored-by: Johannes Gäßler <johannesg@5d6.de> Co-authored-by: Lesaun Harvey <Lesaun@gmail.com>
2023-06-17 11:53:04 +00:00
/server
Make loading weights 10-100x faster This is a breaking change that's going to give you three benefits: 1. Your inference commands should load 100x faster 2. You may be able to safely load models 2x larger 3. You can run many concurrent inference processes This was accomplished by changing the file format so we can mmap() weights directly into memory without having to read() or copy them thereby ensuring the kernel can make its file cache pages directly accessible to our inference processes; and secondly, that the file cache pages are much less likely to get evicted (which would force loads to hit disk) because they're no longer competing with memory pages that were needlessly created by gigabytes of standard i/o. The new file format supports single-file models like LLaMA 7b, and it also supports multi-file models like LLaMA 13B. Our Python tool now merges the foo.1, foo.2, etc. files back into a single file so that the C++ code which maps it doesn't need to reshape data every time. That's made llama.cpp so much simpler. Much of its load code has now been deleted. Furthermore, this change ensures that tensors are aligned properly on a 32-byte boundary. That opens the door to seeing if we can get additional performance gains on some microprocessors, by using ops that require memory alignment. Lastly note that both POSIX and the Windows platform are supported Fixes #91
2023-03-29 20:51:37 +00:00
/Pipfile
llama : support input embeddings directly (#1910) * add interface for float input * fixed inpL shape and type * add examples of input floats * add test example for embd input * fixed sampling * add free for context * fixed add end condition for generating * add examples for llava.py * add READMD for llava.py * add READMD for llava.py * add example of PandaGPT * refactor the interface and fixed the styles * add cmake build for embd-input * add cmake build for embd-input * Add MiniGPT-4 example * change the order of the args of llama_eval_internal * fix ci error
2023-06-28 15:53:37 +00:00
/embd-input-test
gguf : init
2023-07-26 08:16:07 +00:00
/gguf
ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710)
2023-06-06 07:18:03 +00:00
/libllama.so
Add git-based build information for better issue tracking (#1232) * Add git-based build information for better issue tracking * macOS fix * "build (hash)" and "CMAKE_SOURCE_DIR" changes * Redo "CMAKE_CURRENT_SOURCE_DIR" and clearer build messages * Fix conditional dependency on missing target * Broke out build-info.cmake, added find_package fallback, and added build into to all examples, added dependencies to Makefile * 4 space indenting for cmake, attempt to clean up my mess in Makefile * Short hash, less fancy Makefile, and don't modify build-info.h if it wouldn't change it
2023-05-01 16:23:47 +00:00
build-info.h
Initial release
2023-03-10 18:40:58 +00:00
arm_neon.h
compile_commands.json
gitignore : add several entries specific to Visual Studio (#1888)
2023-06-16 06:58:11 +00:00
CMakeSettings.json
Nix flake (#40) * Nix flake * Nix: only add Accelerate framework on macOS * Nix: development shel, direnv and compatibility * Nix: use python packages supplied by withPackages * Nix: remove channel compatibility * Nix: fix ARM neon dotproduct on macOS --------- Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
2023-03-17 22:03:48 +00:00
deploy : add a Package.swift for SwiftPM support (#393) * Add a Package.swift for SwiftPM support * Swap from exclusions to allowlist
2023-03-28 16:39:01 +00:00
__pycache__
zig : add build.zig (#773) Co-authored-by: Locria Cyber <74560659+locriacyber@users.noreply.github.com>
2023-04-05 15:06:02 +00:00
zig-out/
zig-cache/
ggml : use 8-bit precision for Q4_1 intermediate results (#1047) * ggml : use 8-bit precision for Q4_1 intermediate results (ARM) * ggml : optimize ggml_vec_dot_q4_1_q8_0() via vmalq_n_f32 56 ms/token with Q4_1 ! * ggml : AVX2 implementation of ggml_vec_dot_q4_1_q8_0 (#1051) * gitignore : ignore ppl-*.txt files --------- Co-authored-by: slaren <2141330+slaren@users.noreply.github.com>
2023-04-19 17:10:08 +00:00
ppl-*.txt
llama : require first token to be BOS (#1303) * 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
2023-05-08 14:41:54 +00:00
qnt-*.txt
ggml : remove bit shuffling (#1405) * ggml : remove Q4_0 bit shufling (ARM NEON) * ggml : remove Q4_1 bit shuffling (ARM NEON + reference) * ggml : nibbles_from_floats() + bytes_from_nibbles() (ARM NEON) * ggml : remove Q4_2 bit shuffling (WIP, BROKEN) * ggml : remove Q5_0 bit shuffling (ARM NEON) * ggml : 2x faster scalar implementations * ggml : remove Q5_1 bit shuffling (ARM NEON + scalar) * ggml : simplify scalar dot * ggml : remove WASM SIMD bit shuffling + remove vzip for ARM 32-bit * ggml : fix Q4_1 quantization * ggml : update cuBLAS + normalize variable names * ggml : remove Q4_2 mode * ggml : minor formatting * ggml : fix Q5_0 quantization * scripts : add script for measuring the time per token * AVX implementations (#1370) * ggml : uniform 5th bit extraction * llama : produce error upon loading old model files * llama : fix model magic/version write * ggml : speed-up Q5_0 + Q5_1 at 4 threads * ggml : preserve old Q4 and Q5 formats * ggml : simplify Q8_1 - no need for low / high sums anymore * ggml : fix Q8_0 and Q8_1 rounding * Revert "AVX implementations (#1370)" This reverts commit 948d124837f9d287d8490f41338e0e4cceb0814f. * ggml : fix AVX2 implementation * sha : update hashes for 7B and 13B * readme : update timings + remove warning banner * llama : update v2 PR number to 1405 * ggml : fix WASM comments * ggml : back to original bit order * readme : add note that Q4 and Q5 have been changed * llama : fix return for unknown version --------- Co-authored-by: Stephan Walter <stephan@walter.name>
2023-05-11 21:23:08 +00:00
perf-*.txt
examples : add Jeopardy example (#1168) * Basic Setup * Prevent Results.txt from coming up * Prefixes, Line separators, etc * editorcheck * introduction to give more consistent results * Basic graph thing * Grading, ready for testing! * Y'all ready to get funky? * fix column removal stuff * missed a few
2023-04-28 16:13:33 +00:00
examples/jeopardy/results.txt
make : add new target for test binaries (#2244) Programs in the tests directory are now build with target tests and placed in the same location. * clean target was expanded to remove new binaries * test target binaries are listed in a variable * Locations of binaries were added to the .gitignore Signed-off-by: Jiri Podivin <jpodivin@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-21 10:09:16 +00:00
gitignore : changes for Poetry users + chat examples (#2284) A fix in Makefile for FreeBSD users. In the platfrom x86_64 is amd64. This fix resolve compilation using CFLAGS and CXXFLAGS with -march=native and -mtune=native Add two examples for interactive mode using Llama2 models (thx TheBloke for models) Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-21 10:53:27 +00:00
pyproject.toml
poetry.lock
poetry.toml
make : add new target for test binaries (#2244) Programs in the tests directory are now build with target tests and placed in the same location. * clean target was expanded to remove new binaries * test target binaries are listed in a variable * Locations of binaries were added to the .gitignore Signed-off-by: Jiri Podivin <jpodivin@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-21 10:09:16 +00:00
# Test binaries
tests/test-double-float
tests/test-grad0
tests/test-opt
tests/test-quantize-fns
tests/test-quantize-perf
tests/test-sampling
gitignore : fix final newline
2023-07-21 11:42:41 +00:00
tests/test-tokenizer-0
Reference in New Issue Copy Permalink