ipex-llm · Issues· 1484 open

SYCL multi-GPU inference fails with UR_RESULT_ERROR_OUT_OF_DEVICE_MEMORY on Intel Arc Pro (single GPU works)

Docker image update needed to support Kernel 6.18

Could not create a primitive descriptor for a matmul primitive during qwen3 32b inference with portable llama.cpp

llama_load_model_from_file: failed to load model with SYCL/Level Zero on Intel Arc B580 GPU

Intel UHD Graphics 620 supported?

Ollama reports model is 100% on CPU when actually running on GPU

How does ipex_llm overcome the limitation that dynamic input cannot be used on NPUs?

Nonsense output

The Olama version is outdated and cannot load the model

Intel, are you OK?

Update Ollama

Model crashes: IPEX-LLM Ollama v2.3.0-nightly: SIGABRT in sdp_xmx_kernel.cpp with Llama 3.1 on Arc B50 Pro

GPT-OSS 120B ERROR llama.cpp ipex-llm==2.3.0b20251104

ollama version 0.9.3 with latest docker.io/intelanalytics/ipex-llm-inference-cpp-xpu:latest Docker Image

Run DeepSeek-R1 random output on Ollama .