SONG Ge
SONG Ge
> @aahouzi @sgwhat Can you try #6006? Hi @airMeng , it's still not work..., I think my bug is really wired (it could work well on arch linux but not...
> > Hi all @airMeng @NeoZhangJianyu, I also get similar trouble with this issue. > > > > > > GPU device: Arc 770 System: Ubuntu > > > >...
> @sgwhat > > 1. It's hard to know which OPs lead to the error result without deeply check. > 2. We only support llama.cpp issue. > Looks like your...
RuntimeError: Native API failed. Native API returns: -999 (Unknown PI error) -999 (Unknown PI error)
We have reproduced the issue and found a way to optimize it. The corresponding PR will be merged today.
RuntimeError: Native API failed. Native API returns: -999 (Unknown PI error) -999 (Unknown PI error)
Already fixed by https://github.com/intel-analytics/BigDL/pull/10203, could you please have a try? @violet17
The Yuan2 model requires `quantize_kv ` support for the `head_dim` of 64, which only supports 128 for now. I am currently working on it.
Hi @violet17, we are optimizing the model to improve speed.
The exception might be caused by environment issues related to the image. 1. Incompatibility between the Py4J version and PySpark version. 2. Ensure that the Py4J protocol versions used by...
Hi @SjeYinTeoIntel, we do not have a release for pyspark 3.2.2 and ray 2.9.0, but you could run BigDL applications on pyspark 3.2.2. Installing BigDL will automatically install the required...
Below is my implementation for initializing the GPU driver: ```c // Initialize the gpu driver resp->oh.handle = LoadLibrary("C:\Windows\System32\...\ze_loader.dll"); for (i = 0; l[i].s != NULL; i++) { *l[i].p = GetProcAddress(resp->oh.handle,...