ci: remove manual llama.cpp Windows ARM64 build workflow#1194
Merged
Conversation
Mengsheng Wu (mengshengwu)
marked this pull request as ready for review
July 17, 2026 09:56
Its HTP signing duplicates .github/workflows/_build-sdk.yml, which is the release-path source of truth. The workflow was workflow_dispatch only and unreferenced elsewhere. Signed-off-by: Mengsheng Wu <mengshengwu@outlook.com>
Mengsheng Wu (mengshengwu)
force-pushed
the
chore/remove-llama-cpp-windows-ci
branch
from
July 17, 2026 10:01
ef9507e to
f20c3cb
Compare
Maximilien Grzeczka (Maki-Grz)
pushed a commit
to Maki-Grz/GenieX
that referenced
this pull request
Jul 19, 2026
geniex-bench reported the prefill token rate over the raw prompt length, but the QAIRT engine pads input_ids up to the next 128-token chunk before prefill. The reported tok/s therefore understated the work the engine actually did. For qairt cells, round prompt_tokens up to ceil(n/128)*128 and recompute prefill_tps over the padded count. QAIRT's prompt_time equals ttft, so rate stays consistent with prompt_tokens / prompt_time. llama_cpp does no such padding and is left untouched. Closes qualcomm#1194 Signed-off-by: RemiliaForever <remilia@koumakan.cc>
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
.github/workflows/build-llama-cpp-windows.yml, aworkflow_dispatch-only workflow that built upstreamggml-org/llama.cppon thewindows-arm64runner..sosigning (HEXAGON_HTP_CERT_PFX->signtool/inf2cat/.cat) duplicated the release-path signing in.github/workflows/_build-sdk.yml:174-275, which stays as the single source of truth..github/**,notes/**,docs/**, README, CONTRIBUTING).Test plan
git grep -nE 'build-llama-cpp-windows|Build llama\.cpp \(Windows ARM64\)|llama-cpp-windows-arm64' -- ':!third-party' ':!.claude'returns no matches (excluding this PR's own diff).