 Chester Hu
|
689e57bb50
Add inference throughput benchmark on-prem vllm (#331)
|
10 months ago |
|
Chester Hu
|
ff323f49c0
Update delay simulation comment
|
10 months ago |
 Jeff Tang
|
9c039cd122
fix of dead link in demo apps readme (#350)
|
10 months ago |
|
Jeff Tang
|
16aeddac41
fix of dead link
|
10 months ago |
 Hamid Shojanazeri
|
b15ffeeaf4
clean up
|
10 months ago |
|
Hamid Shojanazeri
|
8bf474b455
clean up
|
10 months ago |
|
Hamid Shojanazeri
|
19089269d3
add gc
|
10 months ago |
|
Hamid Shojanazeri
|
dbfea484c6
Feature : Enable Intel GPU/XPU finetuning and inference (#116)
|
10 months ago |
 Danielle Pintz
|
fdc4c64d0b
Update Installation section of README.md
|
11 months ago |
|
Jeff Tang
|
b0646bfd9c
typo fix in Purple_Llama_Anyscale.ipynb (#346)
|
10 months ago |
|
Jeff Tang
|
cc87011701
typo fix in Purple_Llama_Anyscale.ipynb
|
10 months ago |
|
Chester Hu
|
fce0485634
fix type and rename folder names
|
10 months ago |
|
Chester Hu
|
e80c2588a6
Address comments
|
10 months ago |
|
Chester Hu
|
bd3eb3ad95
Update README.md
|
11 months ago |
|
Chester Hu
|
e6a28c7162
Merge branch 'benchmark-infernece-throughput-onperm-vllm' of https://github.com/facebookresearch/llama-recipes into benchmark-infernece-throughput-onperm-vllm
|
11 months ago |
|
Chester Hu
|
2b0fc14081
Update README.md
|
11 months ago |
|
Chester Hu
|
87f6119369
Merge branch 'main' into benchmark-infernece-throughput-onperm-vllm
|
11 months ago |
|
Chester Hu
|
9f84f73420
Address comments
|
11 months ago |
 albertodepaola
|
aaa769c91b
Llama guard data formatter example (#337)
|
11 months ago |
|
Beto
|
6266d31110
changing list to List in the script and test, to attempt to fix issue reported during review
|
11 months ago |
|
Beto
|
bc43c1cf45
Adding steps to the llama guard data sample readme, adding update to main readme.
|
11 months ago |
|
Beto
|
2f6999d205
Fixing error in Readme, adding smaple output
|
11 months ago |
|
albertodepaola
|
2571aeda04
Feature/plotting (#220)
|
11 months ago |
|
Jeff Tang
|
cc107d214c
Merge branch 'main' into benchmark-infernece-throughput-onperm-vllm
|
11 months ago |
|
Beto
|
8d02dae917
formatting the code for readability
|
11 months ago |
|
Beto
|
23299ba10c
fixing typo
|
11 months ago |
|
Beto
|
6e7d005118
Modifying the examples to be more precise. Added example without a model response
|
11 months ago |
|
Beto
|
4a745cc9b5
Adding reference to plot_metrics and save_metrics in the fine tuning section of the readme
|
11 months ago |
|
Beto
|
d85cf35837
Changing the argument from positional to named for better repo consistency
|
11 months ago |
|
Hamid Shojanazeri
|
24ffd96d02
Fix some small nits in README.md (#334)
|
11 months ago |
