GPTQ-triton Alternatives
Similar projects and alternatives to GPTQ-triton
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
dmca
Repository with text of DMCA takedown notices as received. GitHub does not endorse or adopt any assertion contained in the following notices. Users identified in the notices are presumed innocent until proven guilty. Additional information about our DMCA policy can be found at
-
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
GPTQ-triton reviews and mentions
-
The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT
Slightly tangential, but I had intended to start playing around with LLaMA and building some agents. I got the 4-bit versions up and running on my 3090 before I was quickly nerd snipped by a performance problem...
The popular repo for quantizing and running LLaMA is the GPTQ-for-llama repo on github, which mostly copies from the GPTQ authors. The CUDA kernels are needed to support the specific kind of quantization that GPTQ does.
Problem is, while those CUDA kernels are great at short prompt lengths, they fall apart at long prompt lengths. You could see people complaining about this, seeing their inference speeds slowly tanking as their chats/prompts/etc got longer.
So off I went, spending the last week or so re-writing the kernels in Triton. I've now got my kernels running faster than the CUDA kernels at all sizes [0]. And I'm busily optimizing and fusing other areas. The latest MLP fusion kernels gave another couple percentage boost in performance.
Yet I still haven't actually played with LLaMA and made those agents I wanted... sigh And now I'm debating diving into the Triton source code, because they removed integer unpacking instructions during one of their recent rewrites. So I had to use a hack in my kernels which causes them to use more bandwidth than they otherwise should. Think of the performance they could have with those! ... (someone please stop me...)
[0] https://github.com/fpgaminer/GPTQ-triton/
Stats
fpgaminer/GPTQ-triton is an open source project licensed under Apache License 2.0 which is an OSI approved license.
The primary programming language of GPTQ-triton is Jupyter Notebook.
Popular Comparisons
Sponsored