issues
search
srush
/
llama2.rs
A fast llama2 decoder in pure Rust.
MIT License
995
stars
54
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Added modifications I needed to get the project running
#45
AtlasPilotPuppy
opened
7 months ago
0
Exported Models do not load
#44
AtlasPilotPuppy
closed
7 months ago
2
Where is the requirements.export.txt?
#43
sunnyregion
closed
7 months ago
2
How to run baby llama?
#42
tairov
opened
8 months ago
1
Speed comparison
#41
Will-Zhao0
opened
9 months ago
2
CodeLlama support
#40
tonyrewin
opened
9 months ago
1
Model file
#39
srush
closed
9 months ago
0
no `TransformerWeights` in `model`
#38
sunnyregion
closed
9 months ago
3
fabulous, does it support llama 1 and its derivatives anyway?
#37
imkow
opened
10 months ago
2
shrink the IN dim respect to the SIMD
#36
huoyushequ
opened
10 months ago
9
Working CUDA version
#35
srush
closed
9 months ago
7
Non-mmap'ed weights
#34
srush
closed
10 months ago
2
why qzeros need added 1 when unmasked?
#33
huoyushequ
closed
10 months ago
2
Update export.py
#32
huoyushequ
closed
10 months ago
0
Update export.py
#31
huoyushequ
closed
10 months ago
0
Made Python support optional
#30
rachtsingh
closed
10 months ago
1
Pr/rachtsingh/25
#29
srush
closed
10 months ago
0
Max vocab size
#28
srush
closed
10 months ago
0
Small changes to export script
#27
srush
closed
10 months ago
0
[wip] Cuda
#26
srush
closed
10 months ago
2
Python interface
#25
rachtsingh
closed
10 months ago
1
new export script
#24
rachtsingh
closed
10 months ago
0
Tensor has shape torch.Size([448, 1024]) ... this looks incorrect.
#23
timfpark
opened
10 months ago
9
Some llama2 finetunes don't seem to work
#22
balisujohn
opened
10 months ago
2
Fix RoPE and RMS issue
#21
srush
closed
10 months ago
0
License?
#20
1aienthusiast
closed
10 months ago
1
The generation speed is superb, while the context was being truncated.
#19
guoqingbao
closed
7 months ago
18
Fix export problem when using newer version of auto_gptq
#18
guoqingbao
closed
10 months ago
3
Unable to export LLaMa2 model to bin file
#17
guoqingbao
opened
10 months ago
1
Python Versions
#16
VedaRePowered
closed
10 months ago
4
Attempt at a Prefill by expanding matrix expansion
#15
srush
closed
10 months ago
0
Build script
#14
rachtsingh
closed
10 months ago
5
Added rust-toolchain.toml to pin nightly
#13
rachtsingh
closed
10 months ago
0
Configure model size constants using cfg attrs
#12
rachtsingh
closed
10 months ago
2
SIMD Tweaks
#11
srush
closed
10 months ago
0
Attempt to go even faster
#10
mfuntowicz
closed
10 months ago
2
Simplify the simd and remove AVX512 requirement (it doesn't seem to help)
#9
srush
closed
10 months ago
0
Simd version
#8
srush
closed
10 months ago
0
Quick review
#7
CodesInChaos
opened
10 months ago
2
readme commands doesn't work
#6
AsureDay
closed
10 months ago
1
Minor Nitpics, from an also rust newbie :)
#5
cchance27
opened
11 months ago
1
start
#4
srush
closed
11 months ago
0
Static Typing and Sizes
#3
srush
closed
11 months ago
0
Quick Code Review: Auto-vectorization
#2
gaxler
opened
11 months ago
8
nice work, some questions
#1
lucasjinreal
opened
11 months ago
3