提交歷史

作者 SHA1 備註 提交日期
  Alexander Korolev 546e7b2025 glm53-kindling: re-pin BASE to the v0.31.0 release — Docker Hub pruned the entire old nightly-<sha> scheme, the 09-26 base tag is gone and the dir was unbuildable. v0.31.0 (cut 10-02) is the first release containing the base commit; drift audit ddd6fbca..v0.31.0: all patched files unchanged, vllm#58720 landed verbatim upstream (patch dropped, verify-base keeps asserting it), flashinfer 0.7.0->0.7.0.post1, torch/NCCL/cutlass-dsl unchanged 1 周之前
  Alexander Korolev b655965c5f 2x control bench on v2.8.0 (97 scen, hardmode, engine-default effort): 93/100 — the same-harness reference for gr8 (89) and DGPP (88) 1 周之前
  Alexander Korolev 989c085a91 chat template: port the merged GLM-5.3 tool-result fix (HF PR #31) — linear sort-merge pairing replaces the O(N^2) id checks; byte-identical output validated on 3000 randomized conversations; 800 parallel calls render 5.7s -> 0.023s (the old path risked vLLM's 30s render timeout). Checksums change: next serve rebuilds both images 1 周之前
  Alexander Korolev 0acfa6c680 new-engine quality gates on v2.8.0 (97 scen, hardmode, engine-default effort): gr8 full GLM-5.3 TP=4 = 89/100 (decode 49.9 t/s code c1, prefill 1,294 cold/50.9K cached, agg c4 64.6); DGPP Qwen3.8-Flash-Next NVFP4 w1 = 88/100 (def-effort; the low-effort run 86 on 2.7.1.dev7 is a separate datapoint) 1 周之前
  Alexander Korolev 37dc1d74a9 gitignore: per-recipe .lock run ledgers are machine-local state 1 周之前
  Alexander Korolev 94ac882a41 glm53-kindling-4x: 30 GiB hot KV pin (measured headroom; pool 5,083,602 tok) 1 周之前
  Alexander Korolev 606fe37cb4 glm53-kindling-8x: 48 GiB hot KV pin (measured 24-27 GiB/node headroom at 30G) 1 周之前
  Alexander Korolev 58ca8f5034 recipes: glm53-kindling-8x — TP8 on the basic model (b12x load-time head padding, native DFlash2 drafter) 1 周之前
  Alexander Korolev f1c95cde2d README: cluster config is the add-on's sm121_config_extra option (no second repo) 1 周之前
  Alexander Korolev f24e55b2eb README: no cluster config in this (public) repo — it lives in the private cluster-config repo 1 周之前
  Alexander Korolev df46bb8b07 docker-images: sparkring-shared 1 周之前
  Alexander Korolev ad8fb377bf docker-images: solar-open2-nvfp4 1 周之前
  Alexander Korolev 24a8341fad docker-images: qwen38-flashnext-nvfp4 1 周之前
  Alexander Korolev 4d470eb805 docker-images: mimo26-spark-vllm 1 周之前
  Alexander Korolev 760cb3e782 docker-images: mimo26-spark 1 周之前
  Alexander Korolev 50b1f75ee4 docker-images: mia-tp4 1 周之前
  Alexander Korolev 5f21f2baec docker-images: karmic-kraken 1 周之前
  Alexander Korolev bd7380aacd docker-images: jovian-judgement-r39 1 周之前
  Alexander Korolev eb29c35fdf docker-images: jovian-judgement 1 周之前
  Alexander Korolev 9675392c36 docker-images: glm53-kindling 1 周之前
  Alexander Korolev 807beac42b docker-images: glm53-flash-nvfp4-lab 1 周之前
  Alexander Korolev 9ed4603614 docker-images: glm53-flash-nvfp4-4p67 1 周之前
  Alexander Korolev 1c07a9588b docker-images: glm53-flash-nvfp4 1 周之前
  Alexander Korolev b828622aaa docker-images: glm53-flash-exl3 1 周之前
  Alexander Korolev e2d4af3da4 docker-images: glm53-flash-dflash2 1 周之前
  Alexander Korolev c6eb419752 docker-images: glm53-flash-aiden 1 周之前
  Alexander Korolev 3dde0688ae docker-images: glm52-nf3-hybrid 1 周之前
  Alexander Korolev 22b4e641ea docker-images: glm52 1 周之前
  Alexander Korolev 40d2bc57a0 docker-images: dsv41-flash-dcp2 1 周之前
  Alexander Korolev fee7b48cf9 docker-images: dsv41-flash-b12x 1 周之前