-
请问VS-Quant 在哪？
-
Hi! Thank you for releasing this multimodal model. First test are impressive. Even 1.3B is good for its size.
It is just that 7b version in full precision is still taxing on personal HW we have at ho…
-
### 🐛 Describe the bug
When trying to compile a model with the QNN partitioner with the GPU or DSP i get the following error:
```
[ERROR] [Qnn ExecuTorch]: Cannot Open QNN library libQnnDsp.so, w…
-
> The abundance value is simmilar to TPM in RNAseq. It represents the average read coverage of a bin per million reads. So its really a standardized read coverage estimation.
>
> Salm…
-
I have GPU accelerated training with CUDA / ROCm and BitsAndBytes 4-bit quantization working. See https://github.com/instruct-lab/cli/pull/520#issuecomment-1993645744 for more information. However `la…
tiran updated
1 month ago
-
The original 23.8 GB flux1-dev model runs at around the same speed as the 6.8 GB Q4_0 quant that should fit completely into my 12 GB of vram.
This is my workflow:
[workflow.json](https://github.co…
-
Hi,
I would like to ask a question. When I run coloc.abf using coloc version 5.2.3. My input data is as below.
type position snp gARE pvalues beta n
quant 1592964 chr1_1592964_C_T_b38 chr1:169227…
-
TensorRT-LLM has great potential for allowing people to run larger models efficiently with limited hardware resources. Unfortunately, the current quantization workflow requires significant computation…
-
Got this error when running llama_inference.py:
```
$ CUDA_VISIBLE_DEVICES=0 python llama_inference.py ${MODEL_DIR} --wbits 4 --groupsize 128 --load llama7b-4bit-128g.pt --text "this is llama"
Lo…
-
As is, starseqr always requires fatqs even if a STAR alignment is provided. If we modify the salmon call to do alignment mode in this scenario we can bypass the fastq requirement