Optimize NPU performance with KV cache slicing and requantization - #318
Open
zhaixuejun1993 wants to merge 47 commits into
Open
zhaixuejun1993 wants to merge 47 commits into
zhaixuejun1993 wants to merge 47 commits into
Conversation
Assisted-by: Claude Sonnet
…state The stateful path seeds its KV state from ggml's cache when the decode position is ahead of what the state holds. That only works when ggml's cache is a plain prefix, where cell i holds position i. A sliding-window layer keeps just the last n_swa positions and drops the rest, so past the window cell i no longer holds position i and the seeded state is wrong. Slicing the state to the decode position also had no bounds check, so a position past the end surfaced as a bare ov::Exception from the ROI constructor (llama_decode ret = -3, with no reason given at default verbosity). Refuse both cases with a clear message instead, and refuse on the compile path too, where a new model starts with an empty state and so can only serve a sequence from its beginning. Reproducible with llama-bench -d, which restores a saved sequence state rather than recomputing the depth prefill. Assisted-by: Claude Opus 5
The stateful path reinterprets ggml's KV buffer [1, 1, seq, n_heads_kv * head_size] as [1, seq, n_heads_kv, head_size]. The head size is already taken from the tensor's own combined dim, because gemma-4 varies it per layer type, but the head count still came from a model-level scalar that compute_llm_params() overwrites per attention node, so it ended up holding whatever the last layer said. gemma-4 varies the head count per layer too: 12B has 8 x 256 sliding layers and 1 x 512 full layers, 31B has 16 x 256 and 4 x 512. So 40 of 12B's 48 layers were split as 1 x 2048 instead of 8 x 256, and attention read the state with the wrong head split - both models decoded garbage on CPU and GPU. E2B is unaffected, its head count is 1 everywhere. Record the count per layer instead and look it up by the cache_k_l<N> leaf name. Key it by layer, not by layer type: the sliding/full classification comes from cache extents, which tie at a small -c, while the head count does not. The stateful state trim now derives its sequence axis per state for the same reason, since pass::KVStateSeqAxis matches per state on the head count. Assisted-by: Claude Opus 5
pass::KVStateSeqAxis was limited to states with a single KV head, where moving the sequence axis from dim 1 to dim 2 is a pure metadata change. The limit was also based on a measurement showing no gain for a multi-head model, but that was taken at depth 0, which is the one depth where this change does nothing. With several heads the pass does more than move metadata: it drops the reader side transpose of the whole accumulated state, which the graph otherwise redoes every token at a cost that grows with the context length, and replaces it with a transpose of the single new row. Measured on GPU, tg128, alternating arms: gemma-4-12B 6.27 -> 9.11 t/s at depth 8192 (stateless is 7.69, so stateful now wins at depth instead of losing), Llama-3.2-1B 47.8 -> 59.6 t/s. Both are within noise at depth 0, which is why the earlier check saw nothing. The state refill needs the rows copied rather than reinterpreted now: ggml stores [seq][n_heads_kv * head_size], and a relayout state with several heads is a different element order. Without that, a refill would seed wrong data - it is reachable today through llama-bench -d. Assisted-by: Claude Opus 5
Packed QKV views used by mmBERT were rejected by the ROPE support check. This split Q/K RoPE onto CPU, prevented cacheless attention detection, and sent fragmented encoder graphs through the decoder-oriented NPUW path.
Accept packed QKV RoPE views, detect cacheless attention from its mask, and run these models as a single full-sequence prefill without NPUW or a decode graph. Also provide static mask, output index, and mean-pooling shapes and inputs.
Replace the decomposed mean/variance normalization graph with an opset6 MVN operation. This preserves the GGML epsilon placement while allowing OpenVINO plugins to compile normalization as one operation with fewer intermediate tensors.
Cache RoPE sine and cosine outputs in the graph-wide tensor map. Build the cache key from all RoPE parameters and the optional frequency-factor input so compatible Q/K and layer nodes share one subgraph without mixing different RoPE configurations.
Expose NodeContext::put_shared() to publish translator-created outputs for graph-level reuse.
…E/SOFTPLUS cases - translate_add: upcast mismatched operand types (e.g. f16/f32 in fused ADD_ADD) to f32, add, then cast once to the output type. opset1::Add requires matching input types and downcasting first lost precision. - translate_glu_swiglu_clamp: same fix, f16 Swish/Clamp rounding was drifting past the test tolerance. - supports_op: reject ROPE with ne[3] > 1 (multi-sequence) since the cos/sin tables only cover one sequence, and SOFTPLUS on GPU since the OpenVINO GPU kernel overflows to inf for large inputs (CPU is fine). - ci/run.sh: serialize test-backend-ops on OpenVINO GPU; running two workers concurrently crashes the GPU plugin (CL_OUT_OF_RESOURCES).
The ReduceSum shortcut for the MoE expert-plane-sum ADD chain drifts past the 1e-7 test tolerance for >8 experts (f32 accumulation order vs CPU reference), intermittently, like the existing Q4_K/Q5_K NMSE case. Expose is_moe_expert_sum_add() so supports_op can gate on expert count and fall back to CPU for just that reduction op.
CI hit ERR=1.8e-3 (> 5e-4 tolerance) for a scalar-output f32 dot product (m=1,n=1,k=2048); didn't reproduce locally in 8 tries, so likely an internal fp16 accumulation path the GPU plugin picks for this tiny shape. m=1 output dim doesn't occur in real model weights, so gate it.
zhaixuejun1993
requested review from
cavusmustafa and
wine99
as code owners
September 15, 2026 06:27
Add GGML_OPENVINO_NPU_KV_SLICE as an opt-in NPU prefill optimization. When enabled, static prefill keeps the graph's attention dimension at the active prompt/KV length instead of expanding it to the full context capacity, and the KV-cache input/output tensors are bound with a shortened context axis over the same backing storage. This reduces the amount of KV cache and attention-mask data imported by the NPU plugin and lets the prefill graph plan smaller attention buffers for early prompt chunks. For example, with a 4096-token context and a 256-token prefill chunk, the first chunk can expose KV/mask dimensions at 256 instead of 4096, avoiding work over padded cache rows. The trade-off is graph stability: NPU static shapes now depend on the aligned active attention length for prefill, so a cached prefill model is reused only when the attention sizes match. Decode keeps a fixed full-context graph to avoid recompiling on every generated token, and SWA/ring-cache cases still fall back to full-size binding when the live prefix is not a simple leading slice.
Add GGML_OPENVINO_NPU_L0_HOST_TENSORS as an opt-in NPU buffer allocation mode. When enabled, non-remote OpenVINO backend buffers on NPU are allocated through the NPU default context with create_host_tensor(), and ggml tensor data points directly at that OpenVINO-owned Level Zero host allocation. The optimization targets the data path rather than the graph math: KV-cache and compute tensors can be passed back to the NPU plugin as OpenVINO tensors backed by importable Level Zero host memory. That avoids an extra ordinary-host-memory-to-plugin-staging copy on each infer boundary, which is especially useful for prefill where large KV/cache buffers dominate input and output traffic. If Level Zero host allocation fails, the backend logs a warning and falls back to the existing allocation path. The destructor tracks OpenVINO-owned storage so it does not free memory owned by the host tensor. The trade-off is that this is NPU-specific, consumes Level Zero host allocation resources, and improves transfer/import overhead without changing attention compute complexity or tensor shapes.
Add GGML_OPENVINO_NPU_FAST_MASK as an opt-in NPU static prefill input-packing optimization. When enabled, the prefill attention mask is built directly in the OpenVINO input tensor instead of first materializing a padded std::vector and then copying that whole buffer into the tensor. The new fill_prefill_mask() helper writes each row once: it copies the valid mask prefix, fills padding columns with -inf, handles padded rows, and restores the causal diagonal to zero. This keeps the final mask numerically identical to the existing pad_input() plus set_zero_diagonal() path while removing one intermediate allocation and one chunk_size-by-context_size host copy per prefill chunk. The optimization targets CPU-side staging overhead, not attention math. It composes with GGML_OPENVINO_NPU_KV_SLICE: KV slice reduces the mask dimensions, while FAST_MASK reduces the work needed to construct whatever mask shape remains. The trade-off is a second mask construction path to maintain, with limited benefit for very small prompts or contexts.
Add GGML_OPENVINO_NPU_REQUANT_POLICY as the NPU-side selector for the default weight requantization layout. The existing NPU behavior remains the default: unset or group-128 maps quantized weights to Q4_0_128, while channel-wise selects the experimental Q4_0_C layout. Unknown policy values fail fast during model loading instead of silently compiling a graph with unintended weight packing. The optimization target is NPU weight bandwidth and compressed-weight code generation. Q4_0_128 keeps weights in a 4-bit symmetric layout with one scale per 128 values, reducing both payload bytes and scale metadata versus smaller groups while preserving a more conservative quantization granularity than channel-wise. Q4_0_C uses one scale over the innermost dimension, which can further shrink metadata and simplify dequant broadcast, but may cost accuracy because the quantization block is much larger. Include the selected NPU requant policy in the OpenVINO model cache discriminator. The same cgraph compiled with group-128 and channel-wise has different weight constants and dequant shapes, so reusing a cached decoder across policies would be incorrect. This keeps cache reuse stable within a policy while forcing recompilation when the layout policy changes. Trade-off: policy selection gives a performance/accuracy knob for NPU experiments, but all options still pay the load/compile-time requantization cost. The default remains group-128 for a safer balance of bandwidth, metadata, and accuracy; channel-wise is intentionally documented as experimental.
Add GGML_OPENVINO_NPU_CONFIG as the recommended catch-all override for OpenVINO NPU plugin and compiler properties. The value is parsed as comma-separated KEY=VALUE pairs and applied after the built-in defaults and named NPU aliases, so advanced users can override any exposed property without adding a new llama.cpp environment variable for every plugin tuning knob. Keep the common knobs as named aliases for discoverability and compatibility: GGML_OPENVINO_NPU_COMPILER_TYPE maps to NPU_COMPILER_TYPE, GGML_OPENVINO_NPUW_FUNCALL_FOR_ALL maps to NPUW_FUNCALL_FOR_ALL, GGML_OPENVINO_NPUW_UNFOLD_IREQS maps to NPUW_UNFOLD_IREQS, and GGML_OPENVINO_COMPILATION_NUM_THREADS maps to COMPILATION_NUM_THREADS. GGML_OPENVINO_NPU_COMPILE_CONFIG is retained as a legacy alias for NPU_COMPILATION_MODE_PARAMS, while the documentation now recommends expressing it through GGML_OPENVINO_NPU_CONFIG. This keeps the public tuning surface compact while preserving high-signal aliases for settings with known performance or stability implications. NPU_COMPILER_TYPE can select the driver compiler, which currently generates faster prefill kernels on the tested NPU stack. NPUW_FUNCALL_FOR_ALL and NPUW_UNFOLD_IREQS expose NPUW graph lowering trade-offs around dispatch overhead, memory use, and long-context stability. COMPILATION_NUM_THREADS gives a way to cap compiler worker parallelism to reduce peak host memory during large graph compilation. Trade-off: a free-form KEY=VALUE string is less type-safe than one env var per option and invalid plugin properties will only be diagnosed by the OpenVINO stack. Applying it last is intentional: it gives one escape hatch for bisecting driver/compiler behavior and for testing new plugin options without rebuilding llama.cpp, while the named aliases continue to document the most important performance knobs.
Add GGML_OPENVINO_KV_SCATTER_ELEMENTS as an opt-in lowering for non-stateful single-row KV cache writes. When the flag is enabled and the set_rows indices are the simple decode case, translate_set_rows uses ScatterElementsUpdate with broadcasted rank-4 indices instead of ScatterUpdate. The motivation is NPU decode performance. The default ScatterUpdate path updates one KV row but the NPU plugin does not perform that update in place; it effectively copies the full destination tensor to write a small slice. As context length grows, that full-tensor movement dominates the per-token KV update cost. ScatterElementsUpdate expresses the same single-row write at element granularity and is measurably cheaper for this shape. Keep the optimization guarded. Stateful execution keeps its existing concat/update path, and multidimensional indices already use the broader ScatterElementsUpdate lowering. The new flag only changes the common non-stateful decode write, so the default behavior and graph shape remain unchanged unless the user opts in. Trade-off: ScatterElementsUpdate introduces extra ShapeOf, Reshape, and Broadcast nodes to build indices matching the update tensor. That overhead is worthwhile only when it avoids the NPU plugin's full-destination ScatterUpdate copy, so the path is controlled by an environment variable rather than becoming the unconditional lowering.
Add NPU token-embedding controls for models whose token_embd.weight would otherwise be widened from Q6_K to FP16. GGML_OPENVINO_TOKEN_EMBD_I8 keeps the embedding table on the normal int8 compressed-weight path, while GGML_OPENVINO_TOKEN_EMBD_I4 requantizes it to the group-128 int4 layout used by the NPU weight path. The performance target is tied embeddings and large vocabulary tables. When token_embd.weight is also consumed by the lm_head matmul, a normal Gather from the dequantized table gives the dequantization subgraph a second consumer and can force the full table to be materialized. The new gather_compressed_rows helper recognizes the dequantization chain emitted for int4/int8 constants, gathers only the selected packed rows from the leaf constants, and rebuilds the convert/subtract/multiply/reshape chain on those rows. This reduces memory pressure and avoids dequantizing or materializing a full embedding table when inference only needs the token rows for the current input. The helper is deliberately conservative: it only rewrites static 2D tables above a size threshold, walks only the known compressed-weight node patterns, limits recursion depth, and falls back to the original Gather when the subgraph is not recognized. Trade-off: int8 and especially int4 token embeddings can change accuracy and may not be faster for small untied embedding tables, because the rewrite adds extra Gather/Reshape nodes and only pays off when it avoids a large full-table dequantization. The default behavior is unchanged; the NPU-specific I8/I4 paths are opt-in through environment variables.
Extend the GGML_OPENVINO_REDUCE_COMPILE_MEM streaming requantization path to Q4_0/u4 targets. The previous streaming path intentionally skipped u4 because Q4_0 packs two weights per byte and the zero-point tensor stores two 4-bit values per byte, so the original quantize_q4_0 helper wrote as if every call started at block zero. Teach quantize_q4_0 to accept a destination block offset and use the absolute block index for weights, scales, and zero-point writes. Streaming requantization emits whole-row chunks in increasing order, and the target block size is required to divide the row width, so no target block straddles a chunk boundary. That keeps packed weight bytes aligned and preserves the even-block assignment before the odd-block zero-point OR for each shared zero-point byte. With that indexing in place, reduce-compile-memory mode can dequantize a chunk of rows into the scratch buffer and immediately quantize it into the final u4 buffers instead of materializing the entire tensor as temporary F32. This extends the peak-memory reduction already used by Q8/F16 targets to the NPU group-128/channel u4 layouts used for compressed weights. Trade-off: the u4 path is more sensitive to block alignment than Q8/F16 because of nibble packing, so streaming remains guarded by the same row-divisibility check and only runs when GGML_OPENVINO_REDUCE_COMPILE_MEM is enabled. When the flag is off, the full-materialization path and quantized output layout remain unchanged.
Extend the GGML_OPENVINO_RELEASE_WEIGHTS safety check to the static graph cache-miss path. Once host weight buffers have been released, any later compile would read invalid/zeroed host pages and bake the wrong constants into a new OpenVINO model. The dynamic path already rejected this situation. Static execution can still miss the decoder cache when graph shapes or model parameters change, so it needs the same guard before erasing cached infer requests and rebuilding prefill/decode models. This is a correctness and diagnosability change rather than a throughput optimization. It preserves the memory-saving release-weights mode for stable graph shapes, but turns unsupported recompilation into an explicit abort instead of silently producing a corrupted compiled model.
Add GGML_OPENVINO_NPU_KEEP_Q4_0 as an opt-in escape hatch for NPU weight handling. When enabled for native Q4_0 tensors, the NPU requant path returns nullopt and keeps the original Q4_0 extraction instead of regrouping the tensor through the selected NPU requant policy. The motivation is to avoid unnecessary work for weights that are already stored as 4-bit values. The default NPU policy maps quantized weights to layouts such as Q4_0_128, which can reduce scale metadata but requires round-tripping Q4_0 through the requantization path. Keeping Q4_0 native can save that conversion work and preserve the original group-32 packing. Keep the option experimental and disabled by default. Current NPU driver/plugin stacks can compile the resulting group-32 graph, but inference may hang or fail with ZE_RESULT_ERROR_DEVICE_LOST. The default behavior therefore continues to use the safer NPU requant policy; this flag is mainly useful for debugging driver behavior, measuring the true cost of regrouping, and testing future NPU stacks. Trade-off: native Q4_0 avoids regrouping overhead and keeps the original quantization blocks, but it gives up the more regular group-128 layout expected by the default NPU compressed-weight path and may be unstable on current hardware/software combinations.
Compile the static prefill and decode models with separate OpenVINO config maps so the decode graph can opt into NPUW_UNFOLD_IREQS without forcing the same lowering on prefill. The build_static_model helper now receives the config map explicitly, and the decode path gets a copy of the base config with NPUW_UNFOLD_IREQS=YES when the user has not already set it. The performance target is NPU token generation. Decode executes a long stream of single-token infers, where folded NPUW function-call dispatch overhead becomes visible in every token. Unfolding the NPUW calls into separate infer requests removes that repeated dispatch cost and measured about +20% token-generation throughput on the tested stack, matching the behavior seen in OpenVINO GenAI. Prefill keeps the original folded config. Prompt processing is a batched workload dominated by larger matmuls, and the folded form is faster there while also using less memory. Splitting the config lets prefill and decode use the lowering that matches their workload shape instead of treating NPUW_UNFOLD_IREQS as a single global compromise. Trade-off: unfolding can increase memory and request-management overhead, so the automatic default is limited to the NPU decode model. If a user explicitly provides NPUW_UNFOLD_IREQS through the named env alias or GGML_OPENVINO_NPU_CONFIG, that value is respected because the decode override is only applied when the property is absent.
Collect the remaining small cleanups from the NPU tuning series. This reorders the NPU KV-slice documentation and environment-variable cache entry next to the other NPU opt-in toggles, adds a short header comment for the centralized NPU helper declarations, and makes the static prefill attention-size assignment in the decoder a little more explicit. There is no intended behavior change in this commit. The purpose is to make the final source layout match the split commits that introduced the NPU tuning knobs, so future readers can find the related flags and helpers in one place without mixing that mechanical cleanup into the functional performance commits.
Move the default NPU_COMPILER_TYPE=DRIVER setting into the NPU compile_config initializer so the default NPU plugin options are declared in one place. Route GGML_OPENVINO_NPU_COMPILE_CONFIG and GGML_OPENVINO_NPU_COMPILER_TYPE through the same set_compile_option_from_env helper used by the other named NPU compile option aliases. This keeps the legacy NPU_COMPILE_CONFIG mapping to NPU_COMPILATION_MODE_PARAMS intact while making all optional env-to-compile_config overrides follow the same non-empty-value rule. GGML_OPENVINO_NPU_CONFIG is still parsed last, so explicit comma-separated KEY=VALUE overrides continue to have the highest precedence over both defaults and named aliases.
Default the streaming requantization path on for NPU so the compile-time F32 dequant transient (~1-2 GB for token_embd) is capped without an env flag. Output is byte-identical to full materialization; GGML_OPENVINO_REDUCE_COMPILE_MEM / MEMORY_OPTIMIZE still override (set to 0 to force off). Kept the g_nonov_weight_cache opt-in to avoid holding token_embd resident (which regressed decode steady memory). pp1024_d0: PrefillPeakPrivWS 5974->4664 MiB (-22%), decode steady and pp/tg throughput unchanged.
Add an opt-in embedded-weight cache mode for the static NPU backend. GGML_OPENVINO_SELF_CONTAINED_BLOB=1 exports separate prefill and decode compiled models with ENABLE_WEIGHTLESS=false, uses isolated NPUW weight banks, validates raw GGUF weight manifests, binds imported ports by deterministic frontend order, and serializes the large NPUW compile/export/import operations. Preserve raw model bytes during cold cache construction by requantizing into separately owned OV tensors instead of rewriting the backend model buffer. This keeps later graph fingerprints and manifests stable when llama-bench creates independent prompt and generation contexts. Add strict GGML_OPENVINO_SELF_CONTAINED_MMAP=1 warm-import mode. The backend exposes a non-owning buffer_from_host_ptr wrapper over the GGUF mmap, uses raw tensor allocation sizes, avoids allocating/copying the private OpenVINO model-weight buffer, and stages the few mmap-backed runtime constants into small importable NPU host tensors. Invalid or missing cache entries fail clearly instead of trying to requantize into read-only mapped storage. The normal path and existing weightless MODEL_PTR cache remain unchanged when the new flags are unset. Verified with phi-4-mini: chunk512 pp3072/tg512 cold 1123.10/27.60 t/s and warm mmap 1124.72/27.16 t/s; warm mmap removes roughly 3.9 GiB peak commit in the measured prefill workload. Self-contained blobs consume about 8.34 GiB for the separate pp and tg contexts.
zhaixuejun1993
force-pushed
the
xuejun/npu_profiling_v8
branch
from
September 15, 2026 06:43
ff96d07 to
24c7214
Compare
Add GGML_OPENVINO_SELF_CONTAINED_LAZY_IMPORT to make the low-working-set strict mmap path opt in instead of changing the default warm mmap behavior. When the flag is set with SELF_CONTAINED_BLOB=1 and SELF_CONTAINED_MMAP=1, the static NPU path imports only the current phase blob: prefill imports the prefill blob, decode imports the decode blob later. This avoids the pair-shaped shared compiled-model cache for the lazy path and caches only the current phase infer request. The regular warm mmap path remains eager and continues to prepare both prefill and decode compiled models. Non-mmap self-contained builds remain serial, and the regular non-self-contained path keeps the existing parallel build behavior. Also register the new environment variable, document the memory/latency tradeoff, and add profiling-only import timing around model-cache imports. Validated with ReleaseOV build: cmake --build build/ReleaseOV --target llama-bench llama-simple --config Release. Lazy warm mmap run measured PrefillPeakWS around 5759 MiB versus the eager warm mmap path around 7897 MiB.
wine99
force-pushed
the
dev_backend_openvino
branch
from
September 16, 2026 08:07
0365b00 to
37b53fd
Compare
Add GGML_OPENVINO_SELF_CONTAINED_RELEASE_MMAP_PAGES as an explicit opt-in for self-contained compiled-model cache hits. Before importing a valid self-contained blob, recursively walk the graph to find unique external GGUF mmap-backed weight buffers and drop their resident pages while preserving the mapping address and tensor pointers. On Linux use page-aligned madvise(MADV_DONTNEED). On Windows, where there is no reliable per-range mapped-file equivalent, call VirtualUnlock for the identified range and trim the current process working set with SetProcessWorkingSetSize(-1, -1). Pages required later can fault back on demand. Keep the behavior disabled by default and document the physical-memory versus commit-memory tradeoff. Profiling reports the submitted GGUF range and model import duration. Validated with ReleaseOV llama-bench/llama-simple build and pp3072+tg512 warm mmap lazy import. With page release enabled, PrefillPeakWS dropped from about 5758 MiB to 3053 MiB while throughput remained comparable; PeakCommit stayed about 3331 MiB.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces several new OpenVINO NPU (Neural Processing Unit) configuration options, environment variable toggles, and related code logic to enable advanced performance optimizations and flexibility for NPU-based inference. The changes also improve documentation, environment variable handling, and quantization policy logic. Below are the most important changes grouped by theme:
New NPU Configuration and Optimization Options
Added new environment variables and documented options for advanced NPU configuration, including
GGML_OPENVINO_NPU_CONFIG,GGML_OPENVINO_NPU_COMPILER_TYPE,GGML_OPENVINO_NPUW_FUNCALL_FOR_ALL,GGML_OPENVINO_NPUW_UNFOLD_IREQS,GGML_OPENVINO_COMPILATION_NUM_THREADS, andGGML_OPENVINO_NPU_REQUANT_POLICY. These allow fine-grained control over NPU plugin/compiler behavior, compilation threading, and requantization policy. (docs/backend/OPENVINO.md,ggml/src/ggml-openvino/ggml-openvino-extra.cpp,ggml/src/ggml-openvino/ggml-openvino-extra.h) [1] [2] [3] [4] [5] [6]Introduced new NPU-only boolean toggles for experimental and performance features:
GGML_OPENVINO_NPU_FAST_MASK,GGML_OPENVINO_NPU_L0_HOST_TENSORS,GGML_OPENVINO_NPU_KV_SLICE,GGML_OPENVINO_KV_SCATTER_ELEMENTS,GGML_OPENVINO_TOKEN_EMBD_I8,GGML_OPENVINO_TOKEN_EMBD_I4, andGGML_OPENVINO_NPU_KEEP_Q4_0. These enable optimizations such as static prefill mask building, Level Zero host memory for KV-cache, sliced KV prefill graphs, and alternative quantization strategies. (docs/backend/OPENVINO.md,ggml/src/ggml-openvino/ggml-openvino-extra.cpp,ggml/src/ggml-openvino/ggml-openvino-extra.h) [1] [2] [3] [4] [5]NPU Quantization Policy and Weight Handling
Refactored quantization policy logic to support new requantization types and user-specified policies via
GGML_OPENVINO_NPU_REQUANT_POLICY, and added support for experimental embedding-table quantization toggles (GGML_OPENVINO_TOKEN_EMBD_I8,GGML_OPENVINO_TOKEN_EMBD_I4). Also, added logic to optionally skip regrouping of Q4_0 weights for stability. (ggml/src/ggml-openvino/ggml-openvino-extra.cpp,ggml/src/ggml-openvino/ggml-openvino-extra.h) [1] [2]Improved weight buffer handling for self-contained OpenVINO blobs, ensuring the model buffer remains immutable when
GGML_OPENVINO_SELF_CONTAINED_BLOBis enabled. (ggml/src/ggml-openvino/ggml-decoder.cpp)KV-Cache and Attention Mask Shape Handling
ggml/src/ggml-openvino/ggml-decoder.cpp) [1] [2] [3] [4]Documentation and Environment Handling
Expanded documentation in
OPENVINO.mdto describe all new environment variables, their defaults, and their intended use cases, including legacy aliases and override precedence. (docs/backend/OPENVINO.md)Centralized and streamlined environment variable registration and override logic, including parsing comma-separated config overrides for maximum flexibility. (
ggml/src/ggml-openvino/ggml-openvino-extra.cpp)These changes collectively provide much greater control over NPU inference configuration and optimization, as well as improved documentation and maintainability.## Overview
Additional information
Requirements