nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity
2,611 Commits 1 Branch 0 Tags
a307375c02cac45cff53cf2520330b43fecc7718
Commit Graph
60 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Jared Van BortelandGitHub 0a7c980b6f gguf : track writer state, free unneeded tensors, cleanup (#3871) 2023-11-07 12:43:04 -05:00
Jared Van BortelGitHubslaren
 		132d25b8a6 cuda : fix disabling device with --tensor-split 1,0 (#3951) 
Co-authored-by: slaren <slarengh@gmail.com>
 2023-11-05 10:08:57 -05:00
cebtenzzreandGitHub 3fdbe6b66b llama : change yarn_ext_factor placeholder to -1 (#3922) 2023-11-03 08:31:58 +02:00
cebtenzzreGitHubMatheus C. França
 		b12fa0d1c1 build : link against build info instead of compiling against it (#3879) 
* cmake : fix build when .git does not exist

* cmake : simplify BUILD_INFO target

* cmake : add missing dependencies on BUILD_INFO

* build : link against build info instead of compiling against it

* zig : make build info a .cpp source instead of a header

Co-authored-by: Matheus C. França <matheus-catarino@hotmail.com>

* cmake : revert change to CMP0115

---------

Co-authored-by: Matheus C. França <matheus-catarino@hotmail.com>
 2023-11-02 08:50:16 +02:00
cebtenzzreandGitHub 2fffa0d61f cuda : fix RoPE after #2268 (#3897) 2023-11-02 07:49:44 +02:00
cebtenzzreandGitHub 0eb332a10f llama : fix llama_context_default_params after #2268 (#3893) 2023-11-01 19:29:14 -04:00
cebtenzzreGitHubJeffrey Quesnelle
 		898aeca90a llama : implement YaRN RoPE scaling (#2268) 
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
Co-authored-by: Jeffrey Quesnelle <jquesnelle@gmail.com>
 2023-11-01 18:04:33 -04:00
cebtenzzreandGitHub 2046eb4345 make : remove unnecessary dependency on build-info.h (#3842) 2023-10-29 18:33:47 +02:00
cebtenzzreandGitHub 6d459cbfbe llama : correctly report GGUFv3 format (#3818) 2023-10-27 17:33:53 -04:00
cebtenzzreGitHubMichael CoppolaMichael Coppola
 		ad93962657 server : add parameter -tb N, --threads-batch N (#3584) (#3768) 
Co-authored-by: Michael Coppola <m18coppola@gmail.com>
Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
 2023-10-24 23:10:43 +03:00
cebtenzzreandGitHub e78f3ef24a convert : restore compat with old Falcon models (#3680) 2023-10-20 08:32:08 +03:00
cebtenzzreandGitHub 11bff29045 MPT : support GQA for replit-code-v1.5 (#3627) 2023-10-15 09:32:06 +03:00
cebtenzzreandGitHub f1782c68de quantize : fail fast on write errors (#3521) 2023-10-07 11:41:52 +03:00
cebtenzzreGitHubjb
 		48edda30ee convert : update Falcon script for new HF config (#3448) 
Also adds Falcon-180B support.
Closes #3049

Co-authored-by: jb <jonathan.t.barnard@gmail.com>
 2023-10-05 15:00:34 -04:00
cebtenzzreandGitHub 1c84003c08 convert : fix vocab size when not defined in hparams (#3421) 2023-10-02 18:07:24 -04:00
cebtenzzreandGitHub e78f0b0d05 cmake : increase minimum version for add_link_options (#3444) 2023-10-02 22:38:43 +03:00
cebtenzzreandGitHub 29a404a951 gguf : add BERT, MPT, and GPT-J arch info (#3408) 2023-10-02 15:20:28 -04:00
cebtenzzreandGitHub 0fe321031a gguf : general usability improvements (#3409) 2023-10-02 14:58:46 -04:00
cebtenzzreandGitHub 9476b01226 cmake : make CUDA flags more similar to the Makefile (#3420) 
* cmake : fix misuse of cxx_flags

* cmake : make CUDA flags more similar to the Makefile

* cmake : fix MSVC build
 2023-10-02 16:16:50 +03:00
CebtenzzreGitHubGeorgi Gerganov
 		2777a84be4 llama : quantize up to 31% faster on Linux and Windows with mmap (#3206) 
* llama : enable mmap in quantize on Linux -> 31% faster

* also enable mmap on Windows

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-09-29 16:48:45 +03:00
CebtenzzreandGitHub bc39553c90 build : enable more non-default compiler warnings (#3200) 2023-09-28 17:41:44 -04:00
CebtenzzreandGitHub 2db94d98ed gguf : basic type checking in gguf_get_* (#3346) 2023-09-28 14:30:31 -04:00
CebtenzzreandGitHub ecf90b1a51 gguf : make token scores and types optional (#3347) 2023-09-28 14:30:15 -04:00
CebtenzzreandGitHub 20c7e1e804 gguf : fix a few general keys (#3341) 2023-09-27 12:18:07 -04:00
CebtenzzreandGitHub 51a7cf5c6e examples : fix RoPE defaults to match PR #3240 (#3315) 2023-09-23 12:28:50 +03:00
CebtenzzreandGitHub a5661d7e71 llama : allow gguf RoPE keys to be overridden with defaults (#3240) 2023-09-20 12:12:47 -04:00
CebtenzzreandGitHub 65c2c1c5ab benchmark-matmult : do not use integer abs() on a float (#3277) 2023-09-20 12:06:08 -04:00
CebtenzzreandGitHub 8781013ef6 make : restore build-info.h dependency for several targets (#3205) 2023-09-18 10:03:53 -04:00
CebtenzzreandGitHub e6616cf0db examples : add compiler version and target to build info (#2998) 2023-09-15 16:59:49 -04:00
CebtenzzreandGitHub 3aefaab9e5 check C++ code with -Wmissing-declarations (#3184) 2023-09-15 15:38:27 -04:00
CebtenzzreandGitHub 69eb67e282 fix build numbers by setting fetch-depth=0 (#3197) 2023-09-15 15:18:15 -04:00
CebtenzzreandGitHub 80291a1d02 common : do not use GNU zero-length __VA_ARGS__ extension (#3195) 2023-09-15 21:02:01 +03:00
CebtenzzreandGitHub e3d87a6c36 convert : make ftype optional in simple scripts (#3185) 2023-09-15 12:29:02 -04:00
CebtenzzreandGitHub 98311c4277 llama : make quantize example up to 2.7x faster (#3115) 2023-09-14 21:09:53 -04:00
CebtenzzreandGitHub 4b8560e72a make : fix clang++ detection, move some definitions to CPPFLAGS (#3155) 
* make : fix clang++ detection

* make : fix compiler definitions outside of CPPFLAGS
 2023-09-14 20:22:47 +03:00
CebtenzzreandGitHub e64f5b5578 examples : make n_ctx warning work again (#3066) 
This was broken by commit e36ecdcc ("build : on Mac OS enable Metal by
default (#2901)").
 2023-09-08 11:43:35 -04:00
CebtenzzreandGitHub 6336d834ec convert : fix F32 ftype not being saved (#3048) 2023-09-07 14:27:42 -04:00
CebtenzzreGitHubxaedes
 		00d62adb79 fix some warnings from gcc and clang-tidy (#3038) 
Co-authored-by: xaedes <xaedes@gmail.com>
 2023-09-07 13:22:29 -04:00
CebtenzzreandGitHub 4fa2cc1750 make : improve test target (#3031) 2023-09-07 10:15:01 -04:00
CebtenzzreandGitHub 5ffab089a5 make : fix CPPFLAGS (#3035) 2023-09-07 10:13:50 -04:00
CebtenzzreandGitHub 9912b9efc8 build : add LLAMA_METAL_NDEBUG flag (#3033) 2023-09-05 18:21:10 -04:00
CebtenzzreandGitHub 9e2023156e make : use new flag variables for recent changes (#3019) 2023-09-05 15:12:00 -04:00
CebtenzzreandGitHub de2fe892af examples : replace fprintf to stdout with printf (#3017) 2023-09-05 15:10:27 -04:00
CebtenzzreandGitHub 3103568144 llama-bench : make cpp file non-executable (#2999) 2023-09-04 13:40:18 +03:00
CebtenzzreandGitHub bc054af97a make : support overriding CFLAGS/CXXFLAGS/CPPFLAGS/LDFLAGS (#2886) 
* 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
 2023-09-03 08:26:59 +03:00
CebtenzzreandGitHub 6c9c23429b make : use unaligned vector moves on MinGW (#2945) 
Fixes #2922
 2023-09-01 16:53:14 +03:00
CebtenzzreandGitHub ef15649972 build : fix most gcc and clang warnings (#2861) 
* fix most gcc and clang warnings

* baby-llama : remove commented opt_params_adam

* fix some MinGW warnings

* fix more MinGW warnings
 2023-09-01 16:34:50 +03:00
CebtenzzreandGitHub 18705a30ef llama2c : fix segfault and alloc-dealloc-mismatch (#2913) 
* 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
 2023-09-01 12:03:49 +03:00
CebtenzzreandGitHub bce1fef328 convert : fix another python 3.8 issue (#2949) 2023-08-31 22:13:51 -04:00
CebtenzzreandGitHub 92d0b751a7 convert : fix python 3.8 support, modernize type annotations (#2916) 
* 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
 2023-08-31 08:02:23 +03:00
CebtenzzreandGitHub 849408957c tests : add a C compliance test (#2848) 
* tests : add a C compliance test

* make : build C compliance test by default

* make : fix clean and make sure C test fails on clang

* make : move -Werror=implicit-int to CFLAGS
 2023-08-30 09:20:26 +03:00
CebtenzzreandGitHub d4b5e16c32 make : fix clang tests build, add missing examples (#2859) 
* make : do not pass headers to the compiler

This fixes building tests with clang.

* make : add missing examples

* make : fix build-info.h dependencies
 2023-08-29 11:42:41 +03:00
CebtenzzreandGitHub ebcee207b6 quantize : make output filename optional again (#2823) 
* quantize : make output filename optional again

* quantize : fix path parsing on Windows

suggested by @slaren
 2023-08-28 09:32:25 +03:00
CebtenzzreandGitHub 741ca7dd1c llama : move #includes out of _GNU_SOURCE conditional (#2817) 2023-08-26 21:17:51 +03:00
CebtenzzreandGitHub 50526f37eb llama : use std::abs in llama_sample_tail_free (#2800) 
Plain 'abs' casts the input to int.
 2023-08-26 19:53:52 +03:00
CebtenzzreandGitHub 7c2227a197 chmod : make scripts executable (#2675) 2023-08-23 17:29:09 +03:00
CebtenzzreandGitHub 182af739c4 server: regenerate completion.js.hpp (#2515) 2023-08-04 21:00:57 +02:00
CebtenzzreandGitHub 4329d1acb0 CUDA: use min compute capability of GPUs actually used (#2506) 2023-08-04 17:35:22 +02:00
CebtenzzreandGitHub 02f9d96a86 CUDA: check if event is NULL before cudaStreamWaitEvent (#2505) 
Fixes #2503
 2023-08-04 17:34:32 +02:00
CebtenzzreandGitHub 6df1f5940f make : build with -Wmissing-prototypes (#2394) 2023-07-26 21:00:04 +03:00