Block or Report
Block or report Qubitium
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePopular repositories
-
-
-
-
list Public
Forked from javve/list.js
Do you want a 9 KB cross-browser native JavaScript that makes your plain HTML lists super flexible, searchable, sortable and filterable? Yeah! Do you also want the possibility to add, edit and remo…
JavaScript 1
-
-
MurmurHash3PHP Public
Forked from vaizard/abandoned-MurmurHash3PHP
A C++ fork/rewrite of the smhasher project to bring Murmurhash v.3 to the Linux shell and to the PHP scripting language.
C++ 1
75 contributions in the last year
Contribution activity
May 2023
Created 1 commit in 1 repository
Created 2 repositories
- Qubitium/qlora Jupyter Notebook
- Qubitium/llama.cpp C
Created a pull request in fpgaminer/GPTQ-triton that received 5 comments
Replace transformer apply_rotary_pos_emb with triton version
This is a port of https://github.com/qwopqwop200/GPTQ-for-LLaMa/pull/221/files by @aljungberg to this repo. On my 4090 4bit + group-size:512 + true…
Opened 2 other pull requests in 2 repositories
artidoro/qlora
1
merged
fpgaminer/GPTQ-triton
1
closed
Created an issue in artidoro/qlora that received 11 comments
Multi-gpu training example?
Testing 4bit qlora training on 33b llama and the training runs fine on 1x gpu but fails with the following using torchrun on 2x gpu. I am referring…
Opened 4 other issues in 4 repositories
horseee/LLM-Pruner
1
closed
openai/triton
1
open
tailscale/tailscale
1
open
fpgaminer/GPTQ-triton
1
open
Started 1 discussion in 1 repository
openai/triton
-
Trition JIT and code compile failing due to triton 2.1.0 deprecation/method relocation
This contribution was made on May 16



