issues
search
FMInference
/
FlexLLMGen
Running large language models on a single GPU for throughput-oriented scenarios.
Apache License 2.0
9.18k
stars
548
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
ValueError: cannot reshape array of size 0 into shape (7168,28672)
#41
progressionnetwork
opened
1 year ago
1
Add Erebus and GALACTICA support
#40
Sumanai
opened
1 year ago
11
Resolve typos in comments and README
#39
tomaarsen
closed
1 year ago
0
CPU/GPU transfer
#38
sshleifer
closed
1 year ago
2
Revert "replace Argparse by Fire"
#37
Ying1123
closed
1 year ago
0
[Multi-line Chatbot] Multiple line chat answers cut off?
#36
SoftologyPro
opened
1 year ago
3
What's differents in FlexGen and ColossalAI ?
#35
Kuri-su
closed
1 year ago
6
Just a suggestion: Think about what Automatic1111 did to Stable Diffusion
#34
cmp-nct
opened
1 year ago
2
Unable to run the benchmark
#33
fungiboletus
closed
1 year ago
2
Update README
#32
merrymercy
closed
1 year ago
0
Update README.md
#31
zhangce
closed
1 year ago
0
Update README.md
#30
merrymercy
closed
1 year ago
0
PermissionError on delete
#29
xaedes
closed
1 year ago
1
Pass over README
#28
DanFu09
closed
1 year ago
1
Can I use FlaxGen's offloading and compression without caching?
#27
yonikremer
closed
1 year ago
2
something wrong in the google colab
#26
azoth07
opened
1 year ago
0
Fix typos in README
#25
Calamari
closed
1 year ago
1
Question: FlexGen seems slower than simple CPU code, am I missing something? [see discussion]
#24
justheuristic
closed
1 year ago
19
Update README.md
#23
keroro824
closed
1 year ago
0
Is this support korean??
#22
waikoreaweatherpjt
closed
1 year ago
1
replace Argparse by Fire
#21
Borda
closed
1 year ago
2
Doesn't seem to obey --path argument, instead try to download to .cache again
#20
hsaito
opened
1 year ago
4
Suggestion: Add support for different decoding strategies (Top P)
#19
anujnayyar1
opened
1 year ago
2
fix: use perf counter for benchmark timing
#18
kemingy
closed
1 year ago
0
Suggestion: Add Bloom support
#17
robinsongh381
opened
1 year ago
1
Add __init__.py
#16
shughes-uk
closed
1 year ago
0
Update README.md
#15
eltociear
closed
1 year ago
0
Link to paper.pdf is broken
#14
pdh
closed
1 year ago
1
How can I use this project for my own model? Or what are the key lines of code?
#13
guotong1988
closed
1 year ago
1
This project is software or hardware?
#12
guotong1988
closed
1 year ago
1
Out-of-memory during weight download and conversion
#11
xloem
closed
1 year ago
9
Support opt-iml
#10
Ying1123
closed
1 year ago
0
Suggestion: Add GPT-NeoX 20B support
#9
ElleLeonne
closed
1 year ago
0
Improve readme & chatbot
#8
Ying1123
closed
1 year ago
0
Update README.md
#7
keroro824
closed
1 year ago
0
Offloading on Windows?
#6
akhilshastrinet
closed
1 year ago
2
Typo in README
#5
eazel7
closed
1 year ago
0
3090
#4
random452
closed
1 year ago
3
Why is offloading necessary at all?
#3
amogkam
closed
1 year ago
3
Discord Link Is Broken
#2
Marviel
closed
1 year ago
2
Support for RWKV language model
#1
BlinkDL
opened
1 year ago
0
Previous