Repository navigation
ai-rm protocol v0.1: AcceleratorProfile, airm_* metrics and placement in the console - #1
Merged
Merged
Conversation
…acement
Infra > Devices gains a read-only ai-rm panel, shown only when the cluster
has an ai-rm source:
- AcceleratorProfile (airm.ai-computing.io/v1alpha1): vendor, model,
memory, peak TFLOPS with its source; the selected device is marked.
- Prometheus airm_* series with rm-core v0.1 names/units; vendor-derived
tok_s/req_s/power_w/accelerators shown as [vendor] when absent. The
device PWR column prefers airm_power_w{scope="card"}.
- ConfigMap airm-placement (LMD_AIRM_NS, default llm-d): decision + reason.
Without the CRD, series and ConfigMap nothing changes and nothing warns.
ai-rm.yaml declares protocol "0.1", metrics: [].
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
npu-lora now reports training throughput as airm_tok_s{component="npu-lora",run_id=...}
and keeps npu_lora_tokens_per_second as a deprecated alias until protocol 0.2.
Read the shared name first and fall back to the old one.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> # Conflicts: # CHANGELOG.md # src/ui/tests.rs
gspark-etri
added a commit
that referenced
this pull request
Oct 20, 2026
ai-rm protocol v0.1: AcceleratorProfile, airm_* metrics and placement in the console
gspark-etri
added a commit
that referenced
this pull request
Oct 20, 2026
ai-rm protocol v0.1: AcceleratorProfile, airm_* metrics and placement in the console
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Re-opened after the repository was recreated with sanitized public history (the previous PR did not carry over).
AcceleratorProfileCRD (airm.ai-computing.io/v1alpha1): vendor, model, memory, peak TFLOPS, selected deviceairm_*series (rm-core v0.1 names/units); vendor-derived values shown as[vendor]when absent; PWR prefersairm_power_w{scope="card"}airm-placementConfigMap decision and reasonairm_tok_s{component="npu-lora"}first, deprecatednpu_lora_tokens_per_secondas fallback (PROTOCOL §6, review item)🤖 Generated with Claude Code