[gilby]

What this changes

DSpark on Metal: the drafter's weights, the ingest of committed rows, proposals for several slots in one launch and the pass's plan.

Part 14 of 18 of the stack for #1676; stacks on dsv41-metal-pr/13-prompt-suffix (part 13, #1717), on main with parts 1 to 5 (#1705 to #1709) merged.

Receipt

• Environment, with the TensorFold commit, MLX or PyTorch version, machine and GPU, checkpoint and revision: TensorFold 9f16848 on main ad98b60 (native Zig 0.17.0; no MLX or PyTorch); Apple M3 Ultra (60-core GPU), 96 GB, macOS, for the kernel and device tests; checkpoint deepseek-ai/DeepSeek-V4.1-Flash-1017.
• Exactness, from tools/bench_concurrent.py --alone --serial or token_sha against "draft": false: n/a for served output; R rows ingested at once == one at a time, 2 and 3 slots in one pass == each alone (greedy and sampled).
• Decode speed before and after, from tools/bench_openai.py: measured on the last PR of the stack.
• Prompt speed before and after: the cold first request's ttft_s from tools/bench_cache.py --require-cold on a long prompt, or "n/a" with the reason when the change cannot reach prompt processing: measured on the last PR of the stack.
• Tests run, with pass, fail and skip counts: zig build test tf-kernel-contract -Dcpu=apple_m1: exit 0, 625/625 steps succeeded; kernel contract, tf-kernel-contract --only dsv41 (Metal): SUMMARY 89 kernels: 89 pass gates 1-4, 0 fail, 0 known findings; 186 controls: 186 red as planted, 0 missed; 0 limit problems; gates 119115 ms, limits 159 ms; zig build test-dsv41-metal -Dcpu=apple_m1 (the device suite, its own step): exit 0, 7/7 steps succeeded; 28/28 tests passed; python3 tools/zig/lean_check.py: 5131 files, 424 problems, the same count as main (5027 files, 424). Zig's summary counts only the test binaries it ran in that invocation, so the step count is the comparable figure.
• Not run, and why: CUDA: no NVIDIA device here; Metal on M1, M2, M4 and M5: one M3 Ultra only; the release-layer checks (test-dsv41-metal-real, test-dsv41-metal-vision-real) were run at the stack's top and are in dsv41 metal: image prompts #1722's receipt.

Checklist

• Every token still goes through the lane rounds. No serial path, and nothing that needs drafts off.
• Drafted output equals "draft": false, a resumed prompt equals a fresh one, and concurrent equals solo.
• No precision traded for speed. If the bits change, the description says which sums change and why.
• A new or changed GPU kernel is registered with the kernel contract (docs/kernel-contract.md); each backend's SUMMARY line is in the receipt.
• Prompt processing is no slower than the last release.
• The description says which platforms I ran, Metal M1 to M5 and CUDA, and which I could not.
• New tests fail before the change, pass after it, and skip cleanly without their dependency.
• Comments and docstrings are one line. No measurements or history in the source.
• No personal data, machine names, internal hosts or local paths. No AI attribution lines.

[ashhart]

Thanks @gilby: nothing owed for this part. It adds the drafter (Metal pass, plan and key rings, stage encoders, weights) with no new Metal source, only composing kernels the earlier parts gate. It lands after #1717.

[ashhart]

Thanks @gilby. This part landed on main with #1719's merge (cfcbecb), which carries #1712-#1719 as your own commits in order; closing it as included. The same Metal contract, full test and DeepSeek device suite cleared the whole stack.