-
### 🚀 Feature
New advancements bringing quantized LoRA and FSDP together.
https://github.com/AnswerDotAI/fsdp_qlora
### Motivation
Train larger models on consumer GPUs or older generation Da…
-
I installed the command in README.md to train this code on multiple devices, but none of them could achieve the results described in the paper.
On a single 3090 GPU, the best results are:
Image to…
-
When I try to train on single GPU, the error keeps on increasing and I cannot see any good results even thill 38th epoch.
train_class_error starts from 97.88 and deom 19th to 37th epoch its consis…
-
Installed chrome os from rammus board and then leona version 126 on dell Inspiron 3542 i5-4210u with nvidia geforce GPU....
Reinstalled few times but couldn't boot. Does this laptop even support ch…
-
After upgrading claymore to version 10
using this link https://github.com/nanopool/Claymore-Dual-Miner/releases/download/v10.0/Claymore.s.Dual.Ethereum.Decred_Siacoin_Lbry_Pascal.AMD.NVIDIA.GPU.Miner…
-
**Issue by [daveygm](https://github.com/daveygm)**
_Friday Dec 13, 2013 at 06:15 GMT_
_Originally opened as https://github.com/adobe/brackets-shell/pull/399_
----
After enabling the integrated GPU …
-
### 🚀 The feature, motivation and pitch
I am working on the quantization scheme of the large model BitAndBytes, the quantization is very smooth when using transformers, but the inference speed is sti…
-
### Motivation
LMDeploy's 4-bit quantized prefix cache (along with 4-bit AWQ for weights) allows running ~70B models on 48GB of RAM with good performance for many-user scenarios. The prefix cache c…
-
### Problem Description
Composable Kernel currently only contains code to support fused attention (FA2) on RDNA3(+) architectures in the forward direction. This greatly increases the VRAM requirement…
-
Minecraft keeps running with my GTX960 instead of my RTX2070 and I can't figure out how to point it at the correct graphics card.