704b8e29ae
probe(round two): W8A8 int8-dynamic scheme — kernel isolation, raw-op probe, artifact builder support
Amendment to the 08-07 directive, given PR #6's verdict: the isolation experiment already ran and eliminated the directive's stated hypotheses — NaN occurs with synthetic int8 weights (not…
Implemented in PR: anodyine/vllm-omni#6
Verdict in brief: the int8 weight-only compressed-tensors artifact delivers the 3-4 reference capacity and speed (4-ref…
bf65a41ceb
probe(evidence): int8-wo capacity matrix, structure gate, PSNR, Marlin 8-bit NaN isolation (issue 5)
Directive after the int8-wo result (2026-10-08, owner-approved): worth one more bounded round — pivot from quantizer variants to kernel-path isolation.
The convergence is the finding: online-FP8…
321e8bb47f
fix(quant): load offline-quantized compressed-tensors checkpoints directly on CPU under offload
2f8363c5fc
fix(quant): resolve hyphenated registry methods and disk-dict from_config in quant factory
Correction from issue #2's probe (PR #4, commit 4f5f99d8): reinspecting this issue's FP8 artifacts shows both qwen_image_21_fp8_all_rtx3090.png and qwen_image_21_fp8_imgmlp_rtx3090.png are…
Review follow-up (PR #4, commit 4f5f99d8): the fp8 serve row is now in the matrix.
- Capacity — reviewer's projection confirmed:
--enable-cpu-offload --quantization fp8serves all of…
Review answer — fp8 serve row run (commit 4f5f99d8). You were right that the row was missing, and right about the arithmetic: `vllm serve … --enforce-eager --enable-cpu-offload --quantization…
__zcode_status=$? if [ "$__zcode_status" -eq 0 ]; then pwd -P > '/tmp/zcode-4c844978-0de0-4cd6-ac3a-7dee0f7f94fe-cwd'; fi exit "$__zcode_status"
Review finding — one configuration is missing from the 3090 serve matrix: --quantization fp8 (weight-only, Marlin on sm_86).
Issue #1's own addendum validated this exact path on this exact…
Implemented in PR: anodyine/vllm-omni#4
Verdicts (per the issue's three-world taxonomy)
RTX 3090 (24 GB): not-built. No host-DRAM spill path for the…