Skip to content

docs: P4 gate item 2 states the prompts that were run (review note on #2178, Refs #803) #2197

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

Closed
bong-water-water-bong wants to merge 2 commits into from
Closed

docs: P4 gate item 2 states the prompts that were run (review note on #2178, Refs #803) #2197

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
576a1bb
docs: the P4 gate's logits line states the prompts that were run (rev…
Nov 11, 2026
dde861b
Restore the llama.cpp pin: the previous commit swept my checkout's ol…
Nov 11, 2026
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
2 changes: 1 addition & 1 deletion docs/npu-p4-target-split.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,7 +236,7 @@ What is still not wired, and stated as such: `gdn_step`/`attn_step` dispatch nee
## 4. Gate (unchanged from #803)

1. `window11`: 3 greedy prompts, text identical to the current binary.
2. Logits KLD **0** on 8 prompts (the same prompts the hw-gate uses), same model dir and kernel set.
2. Logits KLD **0** on 8 prompts, same model dir and kernel set in both arms. (This line used to ask for the hw-gate's prompts; the row below was run on eight fixed completions and says so.)

**Measured (2026-11-11, on the NPU, under `npu-hold` tickets).** Baseline: the binary at `540e1fd`
(before the decode-family move), run twice as the control. Candidate: `main` at `d0fa51c` (with #2166).
Expand Down
Loading