| .. |
|
dflash2_speculator.py
|
9675392c36
docker-images: glm53-kindling
|
hai 1 semana |
|
draft_trunc.py
|
6e0b9528ac
draft-trunc guard: v0.31.0 is a release build (bare version string, no +g<sha> scm suffix) — pin the guard to the release version, keep the fail-loud semantics
|
hai 1 semana |
|
grouped_topk_router.py
|
5e04b7bfe9
glm53-kindling: rebase the 23 drifted experimental/ overlays onto the v0.31.0 base (10 files carry real drift; 21 auto-merged, 2 hand-merged: rejection_sampler accept_drafts after the gather_draft_sampled() refactor, sm90 _TRITON early-return after the 3-tuple _kv_lens_host). Unrebased overlays reintroduce ddd6fbca-era import blocks on the v0.31.0 tree -> ImportError at boot
|
hai 1 semana |
|
model_runner.py
|
5e04b7bfe9
glm53-kindling: rebase the 23 drifted experimental/ overlays onto the v0.31.0 base (10 files carry real drift; 21 auto-merged, 2 hand-merged: rejection_sampler accept_drafts after the gather_draft_sampled() refactor, sm90 _TRITON early-return after the 3-tuple _kv_lens_host). Unrebased overlays reintroduce ddd6fbca-era import blocks on the v0.31.0 tree -> ImportError at boot
|
hai 1 semana |
|
rejection_sampler.py
|
5e04b7bfe9
glm53-kindling: rebase the 23 drifted experimental/ overlays onto the v0.31.0 base (10 files carry real drift; 21 auto-merged, 2 hand-merged: rejection_sampler accept_drafts after the gather_draft_sampled() refactor, sm90 _TRITON early-return after the 3-tuple _kv_lens_host). Unrebased overlays reintroduce ddd6fbca-era import blocks on the v0.31.0 tree -> ImportError at boot
|
hai 1 semana |
|
speculator.py
|
5e04b7bfe9
glm53-kindling: rebase the 23 drifted experimental/ overlays onto the v0.31.0 base (10 files carry real drift; 21 auto-merged, 2 hand-merged: rejection_sampler accept_drafts after the gather_draft_sampled() refactor, sm90 _TRITON early-return after the 3-tuple _kv_lens_host). Unrebased overlays reintroduce ddd6fbca-era import blocks on the v0.31.0 tree -> ImportError at boot
|
hai 1 semana |
Alexander Korolev
6e0b9528ac
draft-trunc guard: v0.31.0 is a release build (bare version string, no +g<sha> scm suffix) — pin the guard to the release version, keep the fail-loud semantics