 Alexander Korolev
|
4a33f594df
mimo-vllm: garble root cause = instanttensor mis-maps MiMo split-GDN weights; b12x loader contract (mm-encoder-tp-mode weights, full Omni, bf16 KV, VLLM_PLUGINS=b12x_loader); dflash re-enabled per Pro launcher; quality bench started
|
1 mese fa |
|
Alexander Korolev
|
c4668aa86f
mimo-vllm: reopen lane on eugr/spark-vllm-b12x nightly (karmic-kraken: MiMo aux, BLHNC layouts, b12x noncausal, eagle3 unwrap) + b12x linear/moe, CUTE_DSL_ARCH=sm_121a
|
1 mese fa |
|
Alexander Korolev
|
02846405b1
mimo: vLLM+DFlash experiment PARKED (r39 KV-layout wall); findings spec + recipe banner, patches kept for reopen
|
1 mese fa |
|
Alexander Korolev
|
1d0bb43ece
mimo26: vLLM B12X A/B lane recipe + sglang 4x fp8-KV trial rollback
|
1 mese fa |
