-
This is a really exciting advancement in 3D printing. I do wish for Marlin support so I can use it on my Prusa MK4S.
-
**Describe the bug**
When I run speed generation benchmark I get the following message:
> INFO - You passed a model that is compatible with the Marlin int4*fp16 GPTQ kernel but use_marlin is Fal…
-
Is there an easy way to convert gguf to marlin and vice-versa? Any comparisons?
https://github.com/leafspark/AutoGGUF
blap updated
2 months ago
-
### Your current environment
```text
The output of `python collect_env.py`
```
### 🐛 Describe the bug
At https://github.com/vllm-project/vllm/blob/main/csrc/quantization/marlin/sparse/ma…
-
### Your current environment
vllm==0.6.3.post1
### Model Input Dumps
```bash
ValueError: Weight input_size_per_partition = 10944 is not divisible by min_thread_k = 128. Consider reducing tensor_pa…
-
### Description
current jitter settings and Linear advance could be better tuned
### Reproduction steps
```bash
Jitter might be too slow for linear advance to be effective, test newest iteration of…
-
We'd like to add GPTQ support to the spares-marlin kernels so we can get (accurate) perplexity numbers from the neuralmagic 2:4 sparse checkpoint.
@HDCharles wrote GPTQ be easy to generalize to ot…
jcaip updated
4 weeks ago
-
### Your current environment
vllm 0.5.4
### 🐛 Describe the bug
autoawq marlin must with no zero point， but vllm：
```python
def query_marlin_supported_quant_types(has_zp: bool,
…
-
I am using Marlin on SKR 1.4 Turbo.
When I use the probe widget, It fails because it sends:
```
; Z-Probe
G91
G38.2 Z-20 F10
G90
; Set the active WCS Z0
G10 L20 P1 Z19
; Retract from the touc…
-
### Did you test the latest release build?
Yes, and the problem still exists.
### Bug Description
Octoprint's Marlin EEPROM editor plugin (https://github.com/cp2004/OctoPrint-EEPROM-Marlin) v3.3.0 …