mfritsche 137b4ceebe rknpu2: add Q4_K dequant + W4A4_HADAMARD default pattern ...

Q4_K weights previously hit the "Unsupported weight type for NPU pipeline"
assert and fell back to CPU. Route them through dequantize_row_q4_K and map
GGML_TYPE_Q4_K to W4A4_HADAMARD, matching the existing Q4_0 handling.

Note: W4A4_HADAMARD is the lower-accuracy of the two W4A4 pipelines
(bench: 3.17 vs 3.43 tg64 for standard). This is an enablement, not a
performance choice.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EWpfhDgYNA21tETDP9ueBE

2026-07-09 23:24:08 +02:00

..

cmake

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

include

CUDA: lower-case PCI bus id, standardize for ggml (#22820)

2026-05-08 10:09:38 +02:00

src

rknpu2: add Q4_K dequant + W4A4_HADAMARD default pattern

2026-07-09 23:24:08 +02:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

Merge tag 'b9101' into dspark

2026-07-08 21:00:48 +00:00