Vulcan
42388f410d
Update CNAME
2025-08-27 11:34:11 +05:30
Vulcan
5b2822e189
Update README.md
2025-01-16 11:06:22 +05:30
Vulcan
ad2ad4c9ac
Update README.md
2025-01-16 03:15:01 +05:30
Vulcan
e75b947078
+ Header Image
...
Updated Header Image
2025-01-16 03:14:34 +05:30
Vulcan
3d205f9716
Update README.md
2025-01-15 12:46:00 +05:30
Vulcan
3ebea38464
Update LICENSE
2025-01-15 12:41:22 +05:30
Vulcan
13830de2e6
Update LICENSE
2025-01-15 12:28:56 +05:30
Vulcan
2b5299a2f1
Create CNAME
2024-10-23 12:50:00 +05:30
Vulcan
2a52e9d292
Llama 3.1 Support
...
README.md - Added examples and docs for Llama 3.1 usage
run / runq - Llama 3.1 is supported as Llama 3 is supported
2024-07-24 01:56:56 +05:30
Vulcan
3d9ae22541
Update run and runq
...
run - mirror changes to runq
2024-07-20 21:35:09 +05:30
Vulcan
e842bf7118
Update runq.c
...
runq - moarrr openmp/openacc parallel loops
2024-07-20 20:53:25 +05:30
Vulcan
1c47da5ebf
Update runq.c
...
runq - speed up rmsnorm with OpenMP / OpenACC
2024-07-20 19:47:46 +05:30
Vulcan
16e223fbca
Update runq.c
...
runq - Undo #pragma omp parallel sections for matmuls for now as there is no real benefit with low number of cores
2024-07-20 19:20:30 +05:30
Vulcan
725faaa608
Update runq.c
2024-07-20 19:14:56 +05:30
Vulcan
fae1157b0b
runq - Add OpenMP parallel regions
...
runq - Experiment to verify speed up matmuls with OpenMP parallel sections
Ref: https://github.com/karpathy/llama2.c/pull/75
2024-07-20 19:08:18 +05:30
Vulcan
036d7cb9f2
runq - remove blas & optimize
...
runq - optimize matmul and quantization functions with OpenMP
2024-07-20 17:44:29 +05:30
Vulcan
8458b68338
runq and runc tiny fixes
...
runq - add blas for matmul
2024-07-19 14:57:19 +05:30
Vulcan
15549bf818
Update Makefile
...
Fix OPENMP for certain builds
2024-07-13 23:27:20 +05:30
Vulcan
c7336474ef
Update README.md
2024-07-13 16:20:06 +05:30
Vulcan
e893f18a36
Support Llama3 8bit quantized inference
...
runq - add llama3 support
2024-07-12 11:52:03 +05:30
Vulcan
63e69a3ad5
Llama3 Model Export Howto
...
README.md
- Added instructions for exporting and inferring llama3 model.
- Added instructions to build with ArmPL
Makefile
- Small update to info texts
2024-07-10 21:58:40 +05:30
Vulcan
5d981db385
Add llama3 tokenizer export script and tokenizer binary
...
The llama3 tokenizer export script is taken from @jameswdelancey 's llama3.c project:
https://github.com/jameswdelancey/llama3.c
Much appreciation & credits to @jameswdelancey
2024-07-10 10:38:20 +05:30
Vulcan
1be98e214d
Llama3 Support (WIP)
...
use -l 3 option
2024-07-09 12:48:29 +05:30
Vulcan
ed2253b306
Merge remote-tracking branch 'upstream/master'
2024-06-24 08:00:42 +05:30
Andrej
350e04fe35
Merge pull request #514 from jameswdelancey/patch-1
...
Add llama3.c port to README.md
2024-05-29 10:01:04 -07:00
Andrej
2eb7430e1a
Merge pull request #521 from code-cp/patch-1
...
Add another Rust port
2024-05-29 10:00:48 -07:00
Vulcan
cd68846d37
Update README.md
2024-05-16 23:57:43 +05:30
code-cp
c502b6ba4c
Add another Rust port
...
Add my Rust port using Burn
2024-05-12 09:47:36 +08:00
Vulcan
c0679150f4
Update README.md
...
Remove cruft & tease upcoming Llama 3 inference support
2024-05-09 11:21:03 +05:30
James Delancey
e6fd170dc9
Add llama3.c port to README.md
...
A faithful clone of Karpathy's llama2.c (one file inference, zero dependency) but fully functional with LLaMA 3 8B base and instruct models.
2024-04-29 01:48:20 -07:00
Vulcan
2d663734ea
Update README.md
2024-04-06 08:46:29 +05:30
Vulcan
4d6452ed5b
Makefile: LLVM BOLT Support
...
- Makefile: Add LLVM BOLT build
Usage:
make BOLTPREP=1 <target> ; make run_bolt
- run.c / runq.c : Enable exit command in prompt in embedded model builds
- README.md: Update usage
2024-04-05 21:37:48 +05:30
Vulcan
c243fb4122
Update README.md
...
- updated usage
2024-04-01 22:18:39 +05:30
Vulcan
700b980b82
Merge branch 'master' of https://github.com/trholding/llama2.c
2024-04-01 22:10:21 +05:30
Vulcan
1544529a3f
Makefile: C -> LLVM Bitcode -> Transpiled C Debug Build
...
Makefile: C to LLVM bitcode and LLVM bitcode to transpiled C debug build.
Requires clang-17, and llvm-cbe to be compiled and added to path.
Get llvm-cbe (LLVM C Backend) here: https://github.com/JuliaHubOSS/llvm-cbe
README.md: Updated usage
2024-04-01 22:10:08 +05:30
Vulcan
3401c70a40
Update README.md
...
Updated usage
2024-04-01 21:11:14 +05:30
Vulcan
5d2fa995d7
MKL build fix + Matmul debug log build
...
- run.c: added temp matmul debug for action replay
- Makefile: fixed MKL build, added matmul debug log build
2024-04-01 21:07:02 +05:30
Vulcan
bf290a49c5
AVX Support
...
- run.c : AVX support based on https://github.com/karpathy/llama2.c/blob/feature/avx2/run.c but loop unrolled and other improvements
- Makefile: Applied -march=native -mtune=native to most builds
2024-04-01 16:54:07 +05:30
Vulcan
6b3490e85a
Update README.md
...
Added the updated output of 'make' build options.
2024-03-20 18:46:24 +05:30
Vulcan
ef370104a0
Makefile: Support runq builds
...
Usage: make
- Prints all options and the added runq build options.
2024-03-20 18:42:12 +05:30
Vulcan
d62525d980
runq.c - Disabled cblas matmul
...
May need invasive rewrite for 8bit quant. Won't fix.
2024-03-20 17:32:16 +05:30
Vulcan
103d3b147a
Refactor run.c - tiny changes
...
Tiny refactor
2024-03-20 16:53:58 +05:30
Vulcan
dd82c76dce
L2Efy runq.c
...
TODO:
- BLAS builds are broken
- Add to Makefile
2024-03-20 16:43:04 +05:30
Vulcan
13839436c9
Merge remote-tracking branch 'upstream/master'
2024-03-19 21:15:58 +05:30
Vulcan
3fc5375ded
Sync run.c to upstream [WIP]
...
TODO:
Port to latest version of cosmo
Port runq to L2E
Seems to work, not fully tested
2024-03-19 21:14:03 +05:30
Andrej
b3c4b6c3c4
Merge pull request #358 from micsh/patch-1
...
Adding F# Port to README.md
2024-02-12 17:23:39 -08:00
Andrej
b50a7572b3
Merge pull request #440 from neoremind/master
...
Add a Java port information in README.
2024-02-12 17:21:54 -08:00
Andrej
2934c3db73
Merge pull request #433 from mtb0x1/master
...
One web page demo of all rust ports in WASM.
2024-02-12 17:21:34 -08:00
Andrej
e0eb8b29ab
Merge pull request #444 from maxbbraun/patch-1
...
Fix typo in runq.c comment
2024-02-12 17:21:08 -08:00
Andrej
1fb5d150be
Merge pull request #446 from kyoungje/kyoungje-patch-1
...
Update run.ipynb to use export.py and --meta-llama parameter
2024-02-12 17:20:45 -08:00
