 Alexander Korolev
|
c11e975b4e
refactor: rename base image family to jovian-judgement (dir + images + profiles); tag = pin cut + model, :local retired
|
1 месяц назад |
|
Alexander Korolev
|
bbeb6bd553
mxfp4 full recipe: switch to the r37 image - r35's DCP4 sparse decode path crashes on this model (reshape x4 DCP factor in attention.py during graph capture)
|
1 месяц назад |
|
Alexander Korolev
|
36bb9825d6
mxfp4 full recipe: cp-kv-cache-interleave-size 1 - the DCP sparse indexer (DSA top-k path) only supports interleave 1 on r35 (4 is the Flash dense-MLA rule, not this path)
|
1 месяц назад |
|
Alexander Korolev
|
675ccdb307
mxfp4 recipes: --linear-backend marlin - the b12x mxfp4 warmup (ungated) crashes on this checkpoint's shapes (rank 3 vs 4 in b12x dense_gemm); marlin A16 is the guaranteed path
|
1 месяц назад |
|
Alexander Korolev
|
57e6336047
mxfp4 recipes: --linear-backend b12x (native SM120 GEMM) - the flashinfer mxfp4 linear kernel wrongly claims sm_12x support and crashes in cute-dsl mm_fp4; --moe-backend is inert for the compressed-tensors MoE scheme (it picks MarlinExperts itself)
|
1 месяц назад |
|
Alexander Korolev
|
17672b1322
mxfp4 recipes: --moe-backend flashinfer_cutlass (the Sept-tree CLI family; _afp8 was not a valid choice on r35 - first boot argparse)
|
1 месяц назад |
|
Alexander Korolev
|
b5e08df460
glm53 full MXFP4: explicit --moe-backend flashinfer_cutlass_afp8 + document the MXFP4 ingestion path
|
1 месяц назад |
|
Alexander Korolev
|
7535a7d2c4
glm53 full-model lane: retarget to RedHatAI/GLM-5.3-MXFP4 on the r35 jovian stack; delete the OOM-proven NVFP4-Spark variants
|
1 месяц назад |
