 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
|
преди 2 месеца |
|
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)
|
преди 2 месеца |
|
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)
|
преди 2 месеца |
|
Alexander Korolev
|
b5e08df460
glm53 full MXFP4: explicit --moe-backend flashinfer_cutlass_afp8 + document the MXFP4 ingestion path
|
преди 2 месеца |
|
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
|
преди 2 месеца |
