docs: newcomer READMEs for the deployment and quantization modules - #24
Draft
vividf wants to merge 1 commit into
Draft
docs: newcomer READMEs for the deployment and quantization modules#24vividf wants to merge 1 commit into
vividf wants to merge 1 commit into
Conversation
3 tasks
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
vividf
force-pushed
the
pr13-ptv3-onboarding
branch
from
September 7, 2026 05:23
4ded075 to
ad16735
Compare
vividf
force-pushed
the
pr14-module-readmes
branch
from
September 7, 2026 05:23
a88b99c to
51e5a69
Compare
This was referenced Sep 7, 2026
Draft
Draft
quant: declarative quantization (plan/placement, modelopt engine, PTQ/QAT, self-describing ckpt)
#17
Draft
Draft
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack(base
pr-stack-base=7e35d97):#11 → #12 → #13 → #14 → #15 → #16 → #17 → #18 → #19 → #20(CenterPoint 全功能點)→ #21 → #25 → #22 → #23 → #24(= 開發 branch HEAD,逐位元一致)。合併由下而上,每合一層把下一層 base retarget。這個 PR 是什麼
兩份「第一次看這個 framework 的人」導向的模組 README——本 stack 全部設計決策與付過學費的教訓的正式落點:
deployment/README.md(新):三分鐘版(五步流程)、stage-graph 心智模型、三 backend 抽象、same-plan-everywhere 不變量、precision 自動路由表、island 規則手冊(誰進島 4 條、cast 放哪、每條規則違反的實測代價表、「島的 fp32 是記號不是執行精度」)、verification tolerance 哲學、evaluation 怎麼讀、新模型接入六步、檔案地圖、深挖連結。quantization/README.md(重寫為 current-state):三分鐘版(dry_run→quantize→deploy)、宣告 vs 執行、PTQ/QAT workflow 與三個付費教訓(freeze_unquantized / 低 lr / PTQ-first)、INT8-vs-FP8 決策表(兩模型交叉驗證)、新增模型 checklist + 五個已付學費陷阱(各連 repo 內實例)、fp32-typed island 地基聲明;重構時代的診斷與 rename 表縮成歷史指標段。Review 方式
對照代碼讀一遍;引用的檔名/路徑已逐一查證非死連結。內容主張(數字、機制)都有 work_dirs/reviews/ 的報告支撐——README 是入口,報告是證據。
檔案清單(點開)
🤖 Generated with Claude Code