The NVFP4 checkpoint caveat is the one I'd flag loudest, easy to grab
"NVIDIA's official NVFP4 conversion" assuming it's 0731, and end up
running the preview's post-training instead of the version that
actually produced the Terminal Bench/DeepSWE jump. That's the kind of
mismatch that wouldn't show up as an error, just quietly worse agentic
performance with no obvious cause.
The MI325X section is the most useful one practically, actual measured
148.66 GiB resident memory instead of a theoretical estimate, plus the
explicit "4K context, not a 1M deployment" caveat. A lot of deployment
guides let you assume architectural max context is the real ceiling,
good that this doesn't.
The RTX PRO 6000 note to keep MTP/DSpark off because they fail warmup
on sm_120 sparse-MLA is also the kind of thing that saves someone hours
of debugging a silent hang, versus finding out from a GitHub issue
after the fact.
The NVFP4 checkpoint caveat is the one I'd flag loudest, easy to grab "NVIDIA's official NVFP4 conversion" assuming it's 0731, and end up running the preview's post-training instead of the version that actually produced the Terminal Bench/DeepSWE jump. That's the kind of mismatch that wouldn't show up as an error, just quietly worse agentic performance with no obvious cause.
The MI325X section is the most useful one practically, actual measured 148.66 GiB resident memory instead of a theoretical estimate, plus the explicit "4K context, not a 1M deployment" caveat. A lot of deployment guides let you assume architectural max context is the real ceiling, good that this doesn't.
The RTX PRO 6000 note to keep MTP/DSpark off because they fail warmup on sm_120 sparse-MLA is also the kind of thing that saves someone hours of debugging a silent hang, versus finding out from a GitHub issue after the fact.