Repository navigation
chore(pipeline): drop local llama.cpp serving, API-only LLM docs - #231
Merged
Merged
Conversation
Local llama.cpp / Hy-MT2 serving is retired: translation runs only on third-party OpenAI-compatible APIs (HTLB_LLM_*). - delete translate/steps/translate/start-llama-server.sh (only consumer of the local server) - repoint make lint shellcheck scope to translate/llm/translate-wave.sh (the deleted script was the only match of the old glob) - rewrite translate/llm/README.md and .env.example for provider config - translate/README.md, repair docstrings, translation-playbook.md, upstream-sync.md: replace Hy-MT2/llama-server instructions with API-only guidance; keep mechanical-first number repair and the sequential repair invariant (now justified by determinism and rate limits, not server slots)
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
Local llama.cpp / Hy-MT2 serving is retired — translation runs only on third-party OpenAI-compatible APIs (
HTLB_LLM_*). The repo still carried the local-server instructions and launcher, which misleads agents and humans into setting up a local server that is never used.Changes
translate/steps/translate/start-llama-server.sh— the only consumer of the local server.make lintshellcheck scope totranslate/llm/translate-wave.sh(the deleted script was the only match of the oldtranslate/steps/translate/*.shglob, which would have hung lint on an empty match).translate/llm/README.md: rewritten — llama.cpp build/server sections removed, new provider-config (.env) section, kept unit/repair-wave instructions verbatim where still true..env.example: cloud API placeholders instead of127.0.0.1:8080/ Hy-MT2 defaults;HTLB_LLAMA_CTXdropped.translate/README.md,docs/pipeline/translation-playbook.md(ops table now says translation — third-party APIs only, local-Q8 bullets removed, subagent waves cloud-only),docs/pipeline/upstream-sync.mdwording.repair_wave.py,mechanical.py,repair_unit.py): «Hy-MT2 oscillates» → generic LLM wording; the sequential-repair invariant is kept but re-justified (deterministic verify rounds, provider rate limits) instead of llama-server slots.Leftover «Llama» mentions in
book//docs/核实记录/are book content (cited studies) and untouched.Verification
make lint— pass (ruff, djlint, yamllint, shellcheck on new scope)make check-content— all gates pass