 Alexander Korolev
|
96c6bfe777
feat(recipes): lab defaults to --enforce-eager — MTP+CUDA-graphs quality bug confirmed by A/B bench
|
il y a 2 mois |
|
Alexander Korolev
|
28e08afa73
feat(recipes): redhat @ 524288 ctx — pinned 10 GiB KV, autotune off, 4096 chunks, lab image for CC-12.0 topk guards
|
il y a 2 mois |
|
Alexander Korolev
|
3d30d85655
docs(specs): lab /174 explained — TC-53 excluded on 120s infra timeout (score unchanged at 89 either way)
|
il y a 2 mois |
|
Alexander Korolev
|
a0383302e3
docs(specs): redhat MTP reality check — RedHatAI ships mtp as separate -mtp-FP8 variant repos (GLM-5.2 pattern); none for 5.3-Flash yet
|
il y a 2 mois |
|
Alexander Korolev
|
5730abbfee
docs(specs): GLM-5.3-Flash three-way quant benchmark on ds4 (measured)
|
il y a 2 mois |
