ggml-org/llama.cpp b10255

on GitHub

Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874)

• sycl: extend oneDNN SDPA to Q4_0-Q8_0 and F32 KV caches

Extends the oneDNN SDPA path (PR #25222) to handle non-F16 KV caches by
dequantizing or converting K/V to dense FP16 on-device before feeding
them into the SDPA graph. The fused systolic kernel then runs identically
to the native FP16 path.

Supported KV types:

• Q4_0, Q4_1, Q5_0, Q5_1, Q8_0: to_fp16_sycl / to_fp16_nc_sycl
• F32: cont_to_f16_sycl
• BF16 and IQ types are excluded (no conversion kernel available)

Gate: non-F16 requires K >= 1024 and Q >= 32 (prefill only).
F16 KV runs at any length (existing behavior).

Also includes the stream sync fix (stream->wait_and_throw() unconditional,
PR #25741 by @malsbat) and removal of V_is_K_view aliasing (K and V are
always dequantized to separate buffers).

Co-Authored-By: Claude noreply@anthropic.com

• docs: drop GGML_SYCL_FA_DEBUG from SYCL.md (not shipped in this PR)
  Co-Authored-By: Claude noreply@anthropic.com

Co-authored-by: Claude noreply@anthropic.com