Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[SYCL] Support host pinned mem to improve SYCL Host-to-Device Memory Access (#26789)

Browse Source 
* support host pinned mem, ggml_backend_sycl_host_buffer_type_get_max_size,

* fix the thread-safe issue
This commit is contained in:
Neo Zhang
2026-08-13 20:05:33 +03:00
committed by GitHub
parent 2606220d9f
commit a97123e497
2 changed files with 48 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/backend/SYCL.md
+1
View File
@@ -795,6 +795,7 @@ User can use the device management in [docs/multi-gpu.md](https://github.com/ggm
| GGML_SYCL_ENABLE_FLASH_ATTN | 1 (default) or 0| Enable Flash-Attention. It can reduce memory usage. The performance impact depends on the LLM.|
| GGML_SYCL_ENABLE_OPT | 0 or 1 (default)| Enable optimize features for Intel GPUs. (Recommended to 0 for Intel devices older than Gen 10) |
| GGML_SYCL_ENABLE_GRAPH | 0 (default) or 1 | Enable running computations through SYCL Graphs feature. Disabled by default because SYCL Graph is still on development, no better performance. |
| GGML_SYCL_ENABLE_HOST_PINNED_MEM | 0 or 1 (default) | Enable host pinned memory to speed up copy data from host to device. When disable it, host memory will common malloc() on CPU.|
| GGML_SYCL_USE_LEVEL_ZERO_API | 1 (default) or 0 | Use Level Zero API for device memory allocation instead of SYCL. Reduces system RAM usage on Intel dGPUs by avoiding DMA-buf/TTM host memory staging. Requires GGML_SYCL_SUPPORT_LEVEL_ZERO_API=ON at build time. SYCL backend always runs on Level Zero running time even if it's set as OFF (The SYCL api will be usage for memory allocation).|
| GGML_SYCL_ENABLE_DNN | 0 or 1 (default)| Enable running computations through oneDNN and always use oneMKL. |
| GGML_SYCL_FA_ONEDNN | 1 (default) or 0 | Enable the oneDNN fused SDPA (flash-attention) path on supported GPUs. Set to 0 to always use the native SYCL flash-attention kernel. |