ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-28 17:14:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
230 Commits 731 Branches 1 Tag
412b42ed29f4de8f2fc5c323a89fcb23b4acbf84
Commit Graph

230 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
DooWoong Lee (David)
412b42ed29 py : removed unused model variable and verified that the code functions correctly with vocab_only setting. Also confirmed that the code works as expected after running with reduced memory usage due to deletion of no-longer-needed variable. (#547) 2023-03-28 20:02:34 +03:00
Georgi Gerganov
d4cd9f7004 ci : make ctest verbose, hopefully we see what is wrong with the sanitizer 2023-03-28 20:01:09 +03:00
Georgi Gerganov
c4f628288b tests : free llama context at the end of the test 2023-03-28 19:51:55 +03:00
Stephan Walter
188fb59d88 all : be more strict about converting float to double (#458) 
* 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>
 2023-03-28 19:48:20 +03:00
Jed Fox
a9b8ceaea2 deploy : add a Package.swift for SwiftPM support (#393) 
* Add a Package.swift for SwiftPM support

* Swap from exclusions to allowlist
 2023-03-28 19:39:01 +03:00
Stephan Walter
884f88402f ggml : introduce structs for the q4 data blocks (#356) 
* Introduce structs for the q4 data blocks

* ggml : rename quant struct variables + fix ARM_NEON

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2023-03-28 18:56:03 +03:00
Georgi Gerganov
eba3e4dba3 gitignore : add "embedding" 2023-03-28 18:34:35 +03:00
dotpy314
19bf52b793 Check the existence of f16_model_path_base in quantize.py (#574) 
Co-authored-by: Jincheng Miao <jincheng.miao@gmail.com>
 2023-03-28 18:06:28 +03:00
slaren
9ed607fdd5 Fix usage of F16C intrinsics in AVX code (#563) 
* Fix usage of F16C intrinsics in AVX code when F16C is not defined
 2023-03-28 17:26:55 +03:00
anzz1
68f43a13dc main.cpp fixes, refactoring (#571) 
- 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
 2023-03-28 17:09:55 +03:00
RJ Adriaansen
d7f5b1ac65 Add embedding example to Makefile (#540) 2023-03-28 09:11:09 +03:00
Marco Matthies
63d2de599a Fix missing ggml link in cmake for examples/* on w64-mingw32 (#542) 2023-03-27 07:55:26 +03:00
Erik Scholz
2c6eed596e ci: add debug build to sanitizer build matrix (#527) 2023-03-26 15:48:40 +00:00
Stephan Walter
180198d957 Fix undefined variables in debug build, remove unused variables (#531) 2023-03-26 15:34:02 +00:00
Juan Calderon-Perez
47fc0b82b4 Add support for linux/arm64 platform during Docker Builds (#514) 
* Add support for linux/arm64 platform

* Add platform to versioned builds
 2023-03-26 14:48:42 +00:00
Stephan Walter
3b8b2c584a Update README and comments for standalone perplexity tool (#525) 2023-03-26 16:14:01 +03:00
anzz1
a990294c27 [main] fix infinite generation (-n == -1) (#523) 2023-03-26 16:06:10 +03:00
Georgi Gerganov
3600f1d140 Add logo to README.md 2023-03-26 10:20:49 +03:00
Harald Fernengel
85e558b4ad Exit from interactive mode if input stream is bad (#491) 
Allow exiting the interactive prompt also with CTRL-D on Unix and CTRL-Z
on Windows.
 2023-03-26 08:25:46 +03:00
anzz1
5c63c02491 CI: Run other sanitizer builds even if one fails (#511) 
applies only to sanitizer builds so they wont be cancelled
 2023-03-26 00:13:28 +02:00
jp-x-g
9c2b80f69b Clarify console output in convert-pth-to-ggml.py (#512) 
"Processing part 1 of 3" instead of "Processing part 0"
 2023-03-25 23:53:55 +02:00
anzz1
1ea6448129 CMake / CI additions (#497) 
* CMake: Add AVX512 option

* CI: Add AVX/AVX512 builds (Windows)
(AVX512 tests can only be run when the worker happens to support it, building works anyway)

* CMake: Fix sanitizer linkage ( merged #468 )

* CI: Add sanitizer builds (Ubuntu)

* CI: Fix release tagging
(change @zendesk/action-create-release to @anzz1/action-create-release until upstream PR Added commitish as input zendesk/action-create-release#32 is merged)
 2023-03-25 23:38:11 +02:00
anzz1
f8eb92869e (Windows) Set console to UTF-8 on init (#420) 
Sets console codepage to 65001 (CP_UTF8) on start for both input and output, should fix problems with UTF-8 characters.
 2023-03-25 22:29:22 +02:00
Georgi Gerganov
2e01c018d2 Fix colors enabling on WIN32 2023-03-25 21:53:39 +02:00
Georgi Gerganov
9fe0e95688 If n_predict == -1, generate forever 2023-03-25 21:51:41 +02:00
Georgi Gerganov
310d5d09a3 Inifinite generation via context swapping (#71) 2023-03-25 21:36:22 +02:00
Georgi Gerganov
3468a153ba Cleanup STL headers + fix embedding examples + minor stuff 2023-03-25 20:51:14 +02:00
Georgi Gerganov
9d678e17dc Move chat scripts into "./examples" 2023-03-25 20:37:09 +02:00
slaren
4b720d5b92 Add AVX2 implementation of dequantize_row_q4_1 (#505) 2023-03-25 20:31:48 +02:00
Georgi Gerganov
84db7c0b8f 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 20:26:40 +02:00
Georgi Gerganov
56e7297bbd Retire the ggml_mul_mat() branch for transposed src0 (#500) 
* Retire the ggml_mul_mat() for transposed src0

- It can always be made contiguous with ggml_cpy()
- The code is now simplified
- The results are deterministic in respect to num threads

* SIMD-ify dequantize_row_q4_0() for ARM_NEON (#502)

* Attempt to SIMD-ify dequantize_row_q4_0() for ARM_NEON

* Fix dequantization - forgot to interleave the quants
 2023-03-25 19:47:21 +02:00
Georgi Gerganov
d2336726ee Disable prompt verbosity by default and add option to enable (#480) 2023-03-25 17:17:16 +02:00
slaren
432b98793c Add AVX2 implementation of dequantize_row_q4_0 (#467) 2023-03-25 17:06:49 +02:00
Georgi Gerganov
9f8548b2d5 Don't interefe with BLAS for large prompts by running only 1 thread 2023-03-25 17:03:10 +02:00
Georgi Gerganov
f6a2b1fc20 Add longer DAN prompt for testing big batch numbers 2023-03-25 16:49:09 +02:00
slaren
e66804f2d7 Add timings for the prompt evaluation (#478) 2023-03-25 16:34:23 +02:00
Georgi Gerganov
1c1459f073 Remove obsolete information from README 2023-03-25 16:30:32 +02:00
Georgi Gerganov
39ab880ccd Remove obsolete assert and fix compiler warning 2023-03-25 16:22:05 +02:00
Georgi Gerganov
0bbf9a17e7 Fix nasty bug in ggml_compute_forward_mul_mat_f32() and reenable BLAS 2023-03-25 16:10:14 +02:00
anzz1
f60b207880 bounds checking for input prefix (#492) 2023-03-25 14:42:09 +02:00
anzz1
e0522e5dd3 feat: '--in-prefix STRING' option (#426) 
Prefix user inputs with a string
 2023-03-25 14:03:19 +02:00
Jed Fox
3261abc446 Add support for file load progress reporting callbacks (#434) 
* File load progress reporting

* Move llama_progress_handler into llama_context_params

* Renames

* Use seekg to find file size instead

* More correct load progress

* Call progress callback more frequently

* Fix typo
 2023-03-25 07:26:28 +02:00
Doomsdayrs
27d29a069f Add missing struct annotation (#483) 
`llama_sample_top_p_top_k` was missing the struct annotation on line 126.

This causes a compiler issue when being parsed by the Kotlin C interop generator.

This commit fixes the above issue by adding the struct annotation.
 2023-03-25 07:21:24 +02:00
Chris Kuehl
9ba873f48c Fix crash for 65B model with pre-allocated memory (#485) 2023-03-25 06:38:14 +02:00
Georgi Gerganov
0965918677 Disable BLAS altogether - the bug is not just for qunatized mat mul 2023-03-24 23:47:06 +02:00
Georgi Gerganov
76e580d933 Disable BLAS branch in mul_mat - seems there is a bug 2023-03-24 23:39:17 +02:00
Georgi Gerganov
ba186f7f64 Immediately start processing the prompt before user input has been provided (#476) 2023-03-24 23:17:58 +02:00
Georgi Gerganov
92dc17b275 Reduce memory usage and allocate enough memory for largest context (#473) 
* Reduce memory usage and allocate enough memory for large contexts

* Simpler scratch buffer usage

* Reenable BLAS for quantized mul_mat

* Fix number of layers in 30B and 65B

* Fix KV cache size for F32
 2023-03-24 23:17:37 +02:00
Georgi Gerganov
a1a48cfccb Temporary bump the memory buffer size - hopefully fix issues from 483bab2e 2023-03-24 18:23:56 +02:00
Gary Mulder
ccf5a1b08d Update README.md (#444) 
Added explicit **bolded** instructions clarifying that people need to request access to models from Facebook and never through through this repo.
 2023-03-24 15:23:09 +00:00