Nice validation here that my short tutorial on building and publishing a Python library to PyPI works as intended!
OPEN SOURCE
-
Sweagent vs Devin: Speed Trade-offs and Feature Gaps
By
–
i did end up trying sweagent. its definitely faster but also very very workflow specific to making pr’s for issues. needs a lot more work to have the iterative feedback flow of devin. opendevin seems to be closer, but doesnt have browsing yet https://t.co/NXXSggMdyi
— swyx 🐣 (@swyx) 14 avril 2024i did end up trying sweagent. its definitely faster but also very very workflow specific to making pr’s for issues. needs a lot more work to have the iterative feedback flow of devin. opendevin seems to be closer, but doesnt have browsing yet
-
Devin Livestream Challenge: Comparing Devin, OpenDevin, and SWE Agent
By
–
lots of comments from 1 viral youtube from another guy who also hasnt tried devin at all haha. @GergelyOrosz we can livestream to try it out if u want, i got the go ahead to do it, theyre not scared just watch my devin vs opendevin vs swe agent livestream to understand how
-
PyTorch Compile Tutorial: Optimizing Machine Learning Code
By
–
https://
pytorch.org/tutorials/inte
rmediate/torch_compile_tutorial.html
… -
PyTorch Optimization: torch.compile vs Vanilla Performance
By
–
this isn’t comparing to torch.compile, which is the torch-native optimized version, it’s comparing to vanilla pytorch which is notoriously bloated and slow 🙂
-
llm.c Optimization: Matching PyTorch Performance After Bug Fix
By
–
Highly amusing update, ~18 hours later: llm.c is now down to 26.2ms/iteration, exactly matching PyTorch (tf32 forward pass). We discovered a bug where we incorrectly called cuBLAS in fp32 mathmode . And ademeure contributed a more optimized softmax kernel for very long rows
-
DBRX: New Open-Source LLM Outperforms Established Models
By
–
#DBRX is a new general-purpose LLM that outperforms all established open-source models on standard benchmarks!
— Databricks (@databricks) 13 avril 2024
DBRX is incredibly efficient thanks to its fine-grained Mixture-of-Experts architecture. Learn how you can get started👇https://t.co/vtG4r2m5hY pic.twitter.com/9o5agDAJBk#DBRX is a new general-purpose LLM that outperforms all established open-source models on standard benchmarks! DBRX is incredibly efficient thanks to its fine-grained Mixture-of-Experts architecture. Learn how you can get started https://
dbricks.co/49g4ZDt -
llm.c Performance Optimization: Closing Gap with PyTorch
By
–
A few new CUDA hacker friends joined the effort and now llm.c is only 2X slower than PyTorch (fp32, forward pass) compared to 4 days ago, when it was at 4.2X slower The biggest improvements were:
– turn on TF32 (NVIDIA TensorFLoat-32) instead of FP32 for matmuls. This is a -
Bixtral Fine-Tuned Model Approaches Claude Opus Performance
By
–
Bixtral is a beast. A well-done fine-tune doesn’t feel far off from Opus.
-
Jina AI Open Source Repository Availability Question
By
–
The FAQ says the code is open source, but I couldn't find the repo under https://
github.com/jina-ai – is the repo not public yet?