26O07m1

velog

About this offer

```sh python3 - <<'PY' import torch print("torch:", torch. version ) print("CUDA:", torch.version.cuda) print("GPU:", torch.cuda.get_device_name(0)) for name in ("float4_e2m1fn_x2", "float4_e2m1fn"): print(name, getattr(torch, name, None)) print("_scaled_mm:", hasattr(torch, "_scaled_mm")) PY grep -A 15 -B 3 -Ei 'fp4. FAIL|RuntimeError|TypeError|NotImplementedError|unsupported' /var/log/b300_validation/stage1_hw_ /08_fp8_fp4_parallel_qualification.log | tail -80

Offer details

Provider: velog
Source: velog-rss
Score: 54.39
Confidence: 49%

Source evidence

What RADAR observed and classified to build this opportunity. It is what the source published, not a verification that the offer is still active.

VelogObserved: Oct 7, 2026Source reliability: 50%
26O07m1. ```sh python3 - <<'PY' import torch print("torch:", torch. version ) print("CUDA:", torch.version.cuda) print("GPU:", torch.cuda.get_device_name(0)) for name in ("float4_e2m1fn_x2", "float4_e2m1fn"): print(name, getattr(torch, name, None)) print("_scaled_mm:", hasattr(torch, "_scaled_mm")) PY grep -A 15 -B 3 -Ei 'fp4. FAIL|RuntimeError|TypeError|NotImplementedError|unsupported'…
Open source