Historial de Commits

Autor SHA1 Mensaje Fecha
  Alexander Korolev a030038c21 mimo-vllm: persist inductor+triton caches (TORCHINDUCTOR_CACHE_DIR/TRITON_CACHE_DIR + triton mount) — kills TritonBundler cubin-not-found churn hace 3 semanas
  Alexander Korolev 06590549ff mimo-vllm: drop sparkring 20GiB KV pin — GB10 UMA auto-sizing keeps ~54GiB pool; pin would strand 34GiB hace 3 semanas
  Alexander Korolev 1f59f0586e mimo-vllm: adopt sparkring tp4 serve contract (spec5, 16x8192, 20GiB KV pin, bounce loader, BLHNC, A16 lm-head, extended-GID prefill); ring-only transport NOT ported (we're switched) hace 3 semanas
  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 hace 3 semanas
  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 hace 3 semanas
  Alexander Korolev 02846405b1 mimo: vLLM+DFlash experiment PARKED (r39 KV-layout wall); findings spec + recipe banner, patches kept for reopen hace 3 semanas
  Alexander Korolev 1d0bb43ece mimo26: vLLM B12X A/B lane recipe + sglang 4x fp8-KV trial rollback hace 3 semanas