Skip to content

ggml-openvino: forward NPU compilation mode parameters #292

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ravi9 merged 1 commit into from
Aug 27, 2026
Merged

ggml-openvino: forward NPU compilation mode parameters #292

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/backend/OPENVINO.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -713,6 +713,7 @@ Boolean flags follow a uniform convention: set to a **positive integer** (e.g. `
| `GGML_OPENVINO_CACHE_DIR` | String | `not set` | Directory for OpenVINO model caching (recommended: `/tmp/ov_cache`). Enables model caching when set. **Not supported on NPU devices.** |
| `GGML_OPENVINO_COMPILED_MODEL_CACHE_DIR` | String | `not set` | Directory for the frontend compiled-model cache. When set, OpenVINO compiled models are exported as blobs and imported on later runs to skip weight requantization, graph conversion, and compilation for matching single-graph models. |
| `GGML_OPENVINO_PREFILL_CHUNK_SIZE`| Integer | `256` | Token chunk size for **NPU** prefill (NPU-only; ignored on CPU/GPU). Must be a positive integer; otherwise the default is used. |
| `GGML_OPENVINO_NPU_COMPILE_CONFIG` | String | `not set` | NPU-only compiler mode parameters forwarded to OpenVINO as `NPU_COMPILATION_MODE_PARAMS`, for example `optimization-level=3`. |
| `GGML_OPENVINO_STATEFUL_EXECUTION`| Boolean | `0` | Enable stateful KV cache for better performance. Recommended on CPU, GPU. |
| `GGML_OPENVINO_DISABLE_CACHE` | Boolean | `0` | Disable the in-process compiled-model / decoder cache (cache is on by default). Set to `1` to disable. |
| `GGML_OPENVINO_DISABLE_KV_SLICE` | Boolean | `0` | Disable the KV-cache input-tensor slicing optimization (slicing is on by default on CPU/GPU). Set to `1` to disable. |
Expand Down
6 changes: 6 additions & 0 deletions ggml/src/ggml-openvino/ggml-openvino-extra.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@ void ggml_openvino_device_config::init() {
"GGML_OPENVINO_CACHE_DIR",
"GGML_OPENVINO_DEBUG_NODE",
"GGML_OPENVINO_COMPILED_MODEL_CACHE_DIR",
"GGML_OPENVINO_NPU_COMPILE_CONFIG",
// Integer values (use ggml_openvino_getenv_int)
"GGML_OPENVINO_PREFILL_CHUNK_SIZE",
// Boolean toggles (treated as int flags via ggml_openvino_getenv_int)
Expand Down Expand Up @@ -89,6 +90,11 @@ void ggml_openvino_device_config::init() {
compile_config["NPUW_CACHE_DIR"] = cache_dir;
compile_config.insert(ov::cache_mode(ov::CacheMode::OPTIMIZE_SIZE));
}
const char * compilation_mode_params =
ggml_openvino_getenv_str("GGML_OPENVINO_NPU_COMPILE_CONFIG");
if (compilation_mode_params && strlen(compilation_mode_params) > 0) {
compile_config["NPU_COMPILATION_MODE_PARAMS"] = compilation_mode_params;
}
} else if (cache_dir && strlen(cache_dir) > 0) {
compile_config.insert(ov::cache_dir(cache_dir));
compile_config.insert(ov::cache_mode(ov::CacheMode::OPTIMIZE_SIZE));
Expand Down
Loading