tests(fp8): xfail the M=1 scaled_mm apply cases

[sducouedic]

Description

The two FP8 apply_weights tests fail at num_tokens=1: dxp_standalone rejects the fused activation-quantize + _scaled_mm bundle with sbf-ddc: DtException: Illegal ddl (ddl_conversion.cpp:1133). The num_tokens=4/128 cases build the same kernel and pass, so the failure is specific to the M=1 decode bundle, not the FP8 linear path. This marks only that parametrization xfail and keeps the other two shapes as real coverage.

The marker is non-strict deliberately: the shape still compiles on some deeptools builds, and an xpass is the signal that the backend fix landed and the marker can be removed.

Test Plan

• uv run pytest tests/test_fp8_linear.py -m "not upstream" — passed (the M=1 cases xpass on this host).
• bash format.sh — clean for the touched file.

Checklist

• I have read the contributing guidelines
• My code follows the project's code style (run bash format.sh)
• I have added tests for my changes (if applicable)
• I have updated the documentation (if applicable)
• My commits include a Signed-off-by: line (DCO compliance)

[github-actions]

👋 Hi! Thank you for contributing.
Just a reminder: Make sure that your code passes all the linting checks, otherwise your PR won't be able to be merged. To do so, run ./format.sh.
Now you are good to go 🚀.

We also recommend installing prek and configuring it to check your code before every local commit.

[joerunde]

#818 tried to bump rpms to find a fix but we still see failures :(

[spyre-ci]

❌ merge-queue-integration: failure

Plan (build waves + dependencies, per arch)

amd64

flowchart LR
  subgraph Lamd64_0["amd64 L0 · 1 parallel"]
    n_amd64_torch_spyre_torch_spyre_dev["torch-spyre/torch-spyre-dev 🟢<br/>image · 2fdfd201c1b0"]
  end
  subgraph Lamd64_1["amd64 L1 · 1 parallel"]
    n_amd64_hf_adapters_hf_adapters_dev["hf-adapters/hf-adapters-dev 🟢<br/>image · 6beebcd33470"]
  end
  subgraph Lamd64_2["amd64 L2 · 1 parallel"]
    n_amd64_spyre_inference_spyre_inference_dev["spyre-inference/spyre-inference-dev 🔴<br/>image · 329004ccf99a"]
  end
  n_amd64_torch_spyre_torch_spyre_dev --> n_amd64_hf_adapters_hf_adapters_dev
  n_amd64_hf_adapters_hf_adapters_dev --> n_amd64_spyre_inference_spyre_inference_dev
  classDef sPending fill:#eceff1,stroke:#90a4ae,color:#37474f
  classDef sBuilding fill:#fff8e1,stroke:#f9a825,color:#5d4037,stroke-width:2px
  classDef sOk fill:#e8f5e9,stroke:#43a047,color:#1b5e20
  classDef sReused fill:#e3f2fd,stroke:#1e88e5,color:#0d47a1
  classDef sFailed fill:#ffebee,stroke:#e53935,color:#b71c1c,stroke-width:2px
  classDef sDropped fill:#f5f5f5,stroke:#bdbdbd,color:#9e9e9e
  class n_amd64_torch_spyre_torch_spyre_dev sOk;
  class n_amd64_hf_adapters_hf_adapters_dev sOk;
  class n_amd64_spyre_inference_spyre_inference_dev sOk;

Loading

✅ orch trigger-pr-validation — green · arches amd64 · fp amd64=23044001

level	component	arch	build	smoke	unit	integration	trunk	regression	perf
L0	torch-spyre/torch-spyre-dev	amd64	✅ ok	⏳	·	🟢 gha	·	·	·
L1	hf-adapters/hf-adapters-dev	amd64	✅ ok	⏳	·	🟢 gha	·	·	·
L2	spyre-inference/spyre-inference-dev	amd64	✅ ok	🟢	·	·	·	🟡 gha	·

GHA test runs:

• [hf-adapters/amd64] integration: SUCCESS https://github.com/torch-spyre/hf-adapters/actions/runs/34377143935
• [torch-spyre/amd64] integration: SUCCESS https://github.com/torch-spyre/torch-spyre/actions/runs/34377345106
• [spyre-inference/amd64] regression: FAILURE https://github.com/torch-spyre/spyre-inference/actions/runs/34377868730

---

⚠️ advisory failures only — mergeable, see below

Build: built 3

Tests: passed 4 · blocking 0 · advisory 2 · infra/inconclusive 0 · no signal 0

Failures by kind

• ⚠️ advisory (does not block) · spyre-inference/amd64 regression: UNSTABLE
• ⚠️ advisory (does not block) · spyre-inference/amd64 gha:regression: FAILURE

Before merging, consider:

• spyre-inference/amd64 gha:regression, spyre-inference/amd64 regression failed with gating: "unstable" — advisory. It set the build UNSTABLE but does not block the merge. Worth a look, not a stop.

[spyre-ci]

GHA test runs:

• [hf-adapters/x86_64] integration: DISPATCHED https://github.com/torch-spyre/hf-adapters/actions/runs/34377143935

[spyre-ci]

GHA test runs:

• [torch-spyre/x86_64] integration: DISPATCHED https://github.com/torch-spyre/torch-spyre/actions/runs/34377345106

[spyre-ci]

GHA test runs:

• [spyre-inference/x86_64] regression: DISPATCHED https://github.com/torch-spyre/spyre-inference/actions/runs/34377868730