issues
search
tairov
/
llama2.mojo
Inference Llama 2 in one file of pure 🔥
https://www.modular.com/blog/community-spotlight-how-i-built-llama2-by-aydyn-tairov
MIT License
2.09k
stars
140
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
issue with Tinyllama-1.1B
#95
BrunoArsioli
opened
3 months ago
0
Update to Mojo 24.3.0
#94
JuniMay
closed
3 months ago
2
str_concat memory leak
#92
dorjeduck
opened
4 months ago
4
Use String, Dict, and read_bytes to shorten and simplify
#91
mikowals
closed
3 months ago
0
Finalize Update to Mojo 24.2.1
#90
sibarras
closed
3 months ago
1
Update to 24.2 WIP
#89
anthony-chaudhary
closed
5 months ago
6
mojo 24.2.1 errors
#88
oss-maintainer-12
closed
4 months ago
2
How to do inference on GPUs
#87
toutouya
closed
5 months ago
1
Updated gitattributes to show mojo as primary lang
#86
grandimam
closed
4 months ago
1
Crashes when running the example command
#85
CanLikeTo
closed
5 months ago
1
Updates for Mojo 24.1
#82
jackos
closed
6 months ago
1
reduce memory use by streaming file to create weight tensors
#81
mikowals
closed
7 months ago
2
Add support for mojo 0.6
#80
clarkezone
closed
7 months ago
2
avoid data copy when reading files
#79
mikowals
closed
9 months ago
1
Changed vectorize function for tile (with a nelts list) in batch_matmul
#77
andresnowak
opened
10 months ago
8
[Request New Features] Support InternLM
#76
crazysteeaam
opened
10 months ago
0
improve readability in batch_matmul
#75
mikowals
closed
10 months ago
1
Update Mojo to v0.5.0
#74
camegone
closed
10 months ago
1
free all allocated pointers
#73
mikowals
closed
10 months ago
3
Autotune for matmul nelts
#72
andresnowak
closed
5 months ago
3
Dockerfile errors
#71
alexandremendoncaalvaro
opened
10 months ago
0
bugfix: Dockerfile Modular Auth + Conda env
#70
alexandremendoncaalvaro
closed
10 months ago
0
improve speed with fused matrix multiplications
#69
mikowals
closed
10 months ago
13
Bug
#68
1997MarsRover
closed
10 months ago
1
Idea for matmul tiling
#67
andresnowak
opened
10 months ago
6
TODO: implement openai api adapter
#66
shroominic
opened
10 months ago
0
TODO: support quantized models
#65
shroominic
opened
10 months ago
0
TODO: support llama2 7B, 13B
#64
shroominic
opened
10 months ago
0
TODO: write a documentation
#63
shroominic
opened
10 months ago
0
TODO: implement support for code llama models
#62
shroominic
opened
10 months ago
0
Turn on discussions
#60
mikowals
closed
10 months ago
1
Optimized rope_rotation_llama and apply temperature to logits with vectorization
#59
andresnowak
opened
10 months ago
16
HuggingFace demo not working
#58
avi-cenna
closed
10 months ago
3
Do you want to grow this project?
#57
shroominic
opened
10 months ago
2
Unroll vectorisation
#56
miili
closed
10 months ago
1
Do you have a plan to port Stable Diffusion models to mojo?
#55
linhduongtuan
closed
10 months ago
1
✂️ remove call to external os library
#54
shroominic
closed
10 months ago
1
Segmentation fault on M1 Max 32GB
#53
shroominic
closed
10 months ago
3
TODO: Support for gguf models
#52
babycommando
opened
11 months ago
1
error: unable to locate module 'read'
#51
loretoparisi
closed
10 months ago
8
use mojo file reader, remove read/ folder
#50
rd4com
closed
10 months ago
8
fix typos in docker file
#49
mikowals
closed
10 months ago
1
use mojo file reader, remove "read/" folder
#48
rd4com
closed
11 months ago
3
Vectorize temperatures
#47
rd4com
closed
11 months ago
2
Rename cores to workers and set to opimal
#46
jackos
closed
11 months ago
0
typo: Just a little fixing for the rnd_seed
#45
rd4com
closed
11 months ago
1
Add param to set threads
#44
tairov
closed
11 months ago
0
Vectorize temperatures logits
#43
rd4com
closed
11 months ago
4
Updated `algorithm::parallelize` calls to match v0.4.0 parameter changes
#42
theshteves
closed
11 months ago
2
adapt to mojo 0.4
#41
rd4com
closed
11 months ago
4
Next