Skip to content

engine: RAMMAP, NUMA, and telemetry (PR1 of #377 split) - #820

Draft
BColsey wants to merge 1 commit into
JustVugg:devfrom
BColsey:successor/pr1-engine
Draft

engine: RAMMAP, NUMA, and telemetry (PR1 of #377 split)#820
BColsey wants to merge 1 commit into
JustVugg:devfrom
BColsey:successor/pr1-engine

Conversation

@BColsey

@BColsey BColsey commented Aug 4, 2026

Copy link
Copy Markdown

Draft successor β€” supersedes #377. One of three dependent PRs reconstructed file-by-file from the frozen green donor 5f6f31a (onto base 72ddb673). Do not merge #377; it is closed as superseded once all three are open + linked.

Scope

Engine C RAMMAP/NUMA + CUDA accounting, strict telemetry parsing, and their tests/docs. Excludes planning, mounts, lifecycle, benchmark, UI.

  • Engine: c/{colibri.c, backend_cuda.cu, compat.h, st.h, telemetry.h}, c/Makefile, c/resource_plan.py
  • Serve/telemetry: c/openai_server.py (PROF parsing)
  • Tests: test_rammap.c, test_resource_masks.c, test_uring.c, test_serve_sentinel.c, test_backend_cuda.cu, test_rammap_e2e.py (parse logic), test_openai_server.py, test_openai_tools_e2e.py, test_fp8_e2e_repack_load.py, test_resource_plan.py
  • Docs: docs/serve_protocol.md, docs/cuda.md

Reconstruction work

  • STRICTEN PROF telemetry parsing (design L78-80): reject field counts other than 10/17/18; read physical_ssd_valid as == "1" (donor uses bool(int(...))); reject non-finite numerics; a malformed known-kind record is a protocol error.
  • Make docs/serve_protocol.md normative at the PROF contract.
  • Hunk-split c/Makefile (test targets here; install rules β†’ PR2) and test_rammap_e2e.py (parse logic here; live tmpfs cells β†’ PR3).

Dependency

None β€” PR1 is the root. openai_server.py is stdlib-only; C tests compile against PR1 headers only.

Build verification (subagent worktree)

  • make -C c check GREEN end-to-end: C build + 41 test binaries, C suite ALL PASS (0 failures), Python discovery 302 passed / 0 failed / 18 expected skips. Standalone β€” no PR2/PR3 dependency.

Co-Authored-By: Claude <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant