Skip to content

feat: support Iluvatar graph runtime#29

Merged
voltjia merged 1 commit into
InfiniTensor:masterfrom
gongchensu:feat/iluvatar-graph-runtime
Jul 15, 2026
Merged

feat: support Iluvatar graph runtime#29
voltjia merged 1 commit into
InfiniTensor:masterfrom
gongchensu:feat/iluvatar-graph-runtime

Conversation

@gongchensu

@gongchensu gongchensu commented Jul 15, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Add Iluvatar stream capture and graph replay support to src/native/cuda/iluvatar/runtime_.h.
  • Enable test_iluvatar_graph to validate graph capture, instantiation, repeated replay, and resource cleanup.

Motivation

Iluvatar graph runtime support was removed in #25 because it had not been
validated on physical hardware. InfiniLM graph execution requires these runtime
bindings for graph capture and replay.

This change restores the capability after validation on Iluvatar BI-V150 with
CoreX 4.5 and BI-V200 with CoreX 1.2.

Follow-up to #25.

Type of Change

  • feat - new feature / new backend capability / new public API
  • fix - bug fix
  • perf - performance improvement without behavior change
  • refactor - code restructuring without behavior change
  • test - adding or fixing tests only
  • docs - documentation only
  • build / ci - build system or CI configuration
  • chore - tooling, formatting, or other non-code changes
  • Breaking change (requires a ! in the Conventional Commits prefix or a BREAKING CHANGE: footer)

Platforms Affected

  • CPU (WITH_CPU)
  • NVIDIA (WITH_NVIDIA)
  • Iluvatar (WITH_ILUVATAR)
  • Hygon (WITH_HYGON)
  • MetaX (WITH_METAX)
  • Moore (WITH_MOORE)
  • Cambricon (WITH_CAMBRICON)
  • Ascend (WITH_ASCEND)
  • Build system / CMake / generated headers
  • Public headers / installed consumer API
  • Documentation only

Smoke Build and Test Result

paste smoke build and test output here

Test Results on Supported Platforms

Platform Affected Build / Smoke Result Full Result / Notes
CPU
NVIDIA
Iluvatar
Hygon
MetaX
Moore
Cambricon
Ascend
Full `ctest` output (optional)
paste here

Benchmark / Performance Impact

Notes for Reviewers

@gongchensu gongchensu self-assigned this Jul 15, 2026
@voltjia voltjia merged commit 5f91be5 into InfiniTensor:master Jul 15, 2026
4 checks passed
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.

2 participants