Democratizing LLM
- Beijing, China
-
22:47
(UTC +08:00) - https://www.linkedin.com/in/fangjiarui/
- https://www.zhihu.com/people/feifeibear
Block or Report
Block or report feifeibear
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
hpcaitech/ColossalAI
hpcaitech/ColossalAI PublicMaking large AI models cheaper, faster and more accessible
-
Tencent/PatrickStar
Tencent/PatrickStar PublicPatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.
-
Tencent/TurboTransformers
Tencent/TurboTransformers Publica fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
-
LLMSpeculativeSampling
LLMSpeculativeSampling PublicFast inference from large lauguage models via speculative decoding
975 contributions in the last year
| Day of Week | March Mar | April Apr | May May | June Jun | July Jul | August Aug | September Sep | October Oct | November Nov | December Dec | January Jan | February Feb | March Mar | ||||||||||||||||||||||||||||||||||||||||
| Sunday Sun | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Monday Mon | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Tuesday Tue | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Wednesday Wed | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Thursday Thu | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Friday Fri | |||||||||||||||||||||||||||||||||||||||||||||||||||||
| Saturday Sat | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More
Activity overview
Contributed to
feifeibear/LLMSpeculativeSampling,
feifeibear/LLMRoofline,
Oneflow-Inc/slurm-cluster
and 16 other
repositories
Contribution activity
March 2024
Created 13 commits in 2 repositories
Created 2 repositories
-
feifeibear/LLMRoofline
Jupyter Notebook
This contribution was made on Mar 11
-
feifeibear/LLM-Viewer
Python
This contribution was made on Mar 7
Created a pull request in hahnyuan/LLM-Viewer that received 1 comment
Opened 1 other pull request in 1 repository
hahnyuan/LLM-Viewer
1
merged
-
[fix] fix analyze_generate_task bug
This contribution was made on Mar 7
Created an issue in hahnyuan/LLM-Viewer that received 6 comments
How can I get throughput for a generative model
I would like to get the throughput measured by (generated tokens)/(overall latency = prefill+decode elapse). Could you please provide an example of…
6
comments
Opened 1 other issue in 1 repository
hahnyuan/LLM-Viewer
1
open
-
The error between LLM-viewer predicted results and TensorRT-LLM real performance is large.
This contribution was made on Mar 11
25
contributions
in private repositories
Mar 1 – Mar 21






