You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Preset K's implementation is in clean/k (reference, kernels, runtime layer and tests) and its converter map is data/preset-K.v1.map.json, but 0.6.0 is built without it: -DWG_MODEL_K=OFF for the front end, --no-model-k for
the runtime, -DWRONGGPU_PRESET_K=OFF for the launcher (BUILDING.md).
To do: build with Preset K turned on, run the CPU tests of clean/k/tests (the modules that need a GPU are listed in
BUILDING.md, section 6), fix what breaks, and test in games on a Radeon RX 9000-series card. A pull request that turns
the options back on says what was tested and where.
Some first in-game numbers for Model K, for whatever they're worth. Please read the caveats first: none of this is a release build or a supported setup.
Caveats
Linux, Cyberpunk 2077 under Proton (GE-Proton11-11), not Windows. One game, one machine.
The installed front end is the 0.6.0 release, which doesn't know Model K; K was selected with WG_RUNTIME_OPTIONS=model=K (the overlay still says Model M).
The model is converted locally from the game's own nvngx_dlss.dll (310.9.1.0, preset K; all 12 stage digests matched). Nothing of it leaves the machine.
Times are the runtime's own GPU timestamps (timing_log=1;timing_stages=1), median of the 300-frame windows of one session each; 1706x960 -> 2560x1440 (1440p Quality), max settings, no RT, no Ray Reconstruction. Not a controlled benchmark.
On both cards K shows flicker on thin bright detail (lit floor grates, neon edges), some ghosting on moving thin objects, and occasional single-pixel specks. It looks the same on both cards.
I don't think it is a WrongGPU porting bug. Offline, with captured real game frames replayed through the runtime, the 7900 XT output matched the in-game output byte for byte. Your NumPy reference of K, run from the captured history and inputs, reproduced the same specks at the same pixels (e.g. 27,986 vs 27,987 one-frame specks in one 30-frame capture), and every stage stayed inside spec 49's limits. So it looks like K's own response to this game's inputs.
k_approx=a1 saved about 0.3 ms on the 7900 XT, but in game it looked clearly worse to me, although a replay of 30 captured frames shows only a small per-frame difference (it sits on thin bright lines and grows over the frames through the history). Worth a look on your side before recommending it.
Happy to share the capture tooling or rerun anything specific.
Activity
Model K: the exposure rule in NumPy (which exposure value is which), …
Model K (HIP): spec-draft-3 exposure rule on the GPU, exact input sta…
Model K on D3D12: build option, struct arguments, the port check, and…
Model K on D3D12: the narrow network stages (k_block.co), byte-identi…
Model K on D3D12: the wide network stages (k_block_wide.co), byte-ide…
Model K on D3D12: the exact tiled input stage (k_io_exact.co), byte-i…
Model K on D3D12: the output stage (k_io.co), byte-identical to HIP
Model K: the launcher's per-game model choice K and the front end's K…
Model K on D3D12: the runtime on the hybrid and native D3D12 devices,…
j0nsh1n commentedon Nov 17, 2026
Some first in-game numbers for Model K, for whatever they're worth. Please read the caveats first: none of this is a release build or a supported setup.
Caveats
WG_RUNTIME_OPTIONS=model=K(the overlay still says Model M).k_smx_test=mix_uncheckedhook.nvngx_dlss.dll(310.9.1.0, preset K; all 12 stage digests matched). Nothing of it leaves the machine.timing_log=1;timing_stages=1), median of the 300-frame windows of one session each; 1706x960 -> 2560x1440 (1440p Quality), max settings, no RT, no Ray Reconstruction. Not a controlled benchmark.Numbers (GPU time per frame, median)
smx=mix)k_approx=a1Image quality
k_approx=a1saved about 0.3 ms on the 7900 XT, but in game it looked clearly worse to me, although a replay of 30 captured frames shows only a small per-frame difference (it sits on thin bright lines and grows over the frames through the history). Worth a look on your side before recommending it.Happy to share the capture tooling or rerun anything specific.