kilork cc41c48e03 glm53 spark recipe: full lil policy alignment (b12x linear/moe backends, k=5 MTP + moe_backend, instanttensor load, mamba-cache-mode align, INSTANTTENSOR env) + mounted pre-baked JIT caches (~/sm121-cache/glm53-jit-121f, dsv4 pattern); boot 35m -> 7m, exact-391 verified 1 месяц назад
..
mods ac5c6c9108 NVFP4-Spark serving on our r12 fork build: spec-config attention_backend=B12X fixes MTP draft selection; intel recipe retargeted; ledger 1 месяц назад
recipe.toml cc41c48e03 glm53 spark recipe: full lil policy alignment (b12x linear/moe backends, k=5 MTP + moe_backend, instanttensor load, mamba-cache-mode align, INSTANTTENSOR env) + mounted pre-baked JIT caches (~/sm121-cache/glm53-jit-121f, dsv4 pattern); boot 35m -> 7m, exact-391 verified 1 месяц назад