| .. |
|
deepseek-v4-flash-dspark
|
12ebaf75c1
docker-images: deepseek-v4-flash-dspark
|
1 주 전 |
|
deepseek-v4-flash-dspark-src
|
487370708d
docker-images: deepseek-v4-flash-dspark-src
|
1 주 전 |
|
deepseek-v4-flash-dspark38
|
3e874b1ef5
docker-images: deepseek-v4-flash-dspark38
|
1 주 전 |
|
deepseek-v4-flash-eugr
|
51e4dedcf0
docker-images: deepseek-v4-flash-eugr
|
1 주 전 |
|
dsv4-flash-vision
|
bfeebc41cb
docker-images: dsv4-flash-vision
|
1 주 전 |
|
dsv41-flash
|
c94a161a26
docker-images: dsv41-flash
|
1 주 전 |
|
dsv41-flash-b12x
|
fee7b48cf9
docker-images: dsv41-flash-b12x
|
1 주 전 |
|
dsv41-flash-dcp2
|
40d2bc57a0
docker-images: dsv41-flash-dcp2
|
1 주 전 |
|
dsv41-sglang-1017
|
fc1850811d
dsv41-sglang-1017: version the image tag v1 (not :local) — trackable and rollback-able
|
5 일 전 |
|
dsv41-tf-1017
|
ec17b00796
dsv41-flash-1017-2x-tensorfold: ship it as an sm121 recipe
|
4 일 전 |
|
glm52
|
22b4e641ea
docker-images: glm52
|
1 주 전 |
|
glm52-nf3-hybrid
|
3dde0688ae
docker-images: glm52-nf3-hybrid
|
1 주 전 |
|
glm53-flash-aiden
|
c6eb419752
docker-images: glm53-flash-aiden
|
1 주 전 |
|
glm53-flash-dflash2
|
e2d4af3da4
docker-images: glm53-flash-dflash2
|
1 주 전 |
|
glm53-flash-exl3
|
b828622aaa
docker-images: glm53-flash-exl3
|
1 주 전 |
|
glm53-flash-nvfp4
|
1c07a9588b
docker-images: glm53-flash-nvfp4
|
1 주 전 |
|
glm53-flash-nvfp4-4p67
|
9ed4603614
docker-images: glm53-flash-nvfp4-4p67
|
1 주 전 |
|
glm53-flash-nvfp4-lab
|
807beac42b
docker-images: glm53-flash-nvfp4-lab
|
1 주 전 |
|
glm53-kindling
|
8678fa1883
kindling: AGENTS checklist for changing the vLLM base (overlay rebase + version guards + post-bake smoke)
|
1 주 전 |
|
jovian-judgement
|
eb29c35fdf
docker-images: jovian-judgement
|
1 주 전 |
|
jovian-judgement-r39
|
bd7380aacd
docker-images: jovian-judgement-r39
|
1 주 전 |
|
karmic-kraken
|
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 주 전 |
|
mia-tp4
|
50b1f75ee4
docker-images: mia-tp4
|
1 주 전 |
|
mimo26-spark
|
760cb3e782
docker-images: mimo26-spark
|
1 주 전 |
|
mimo26-spark-vllm
|
4d470eb805
docker-images: mimo26-spark-vllm
|
1 주 전 |
|
nemotron-bolt-b12x
|
a972f8b214
nemotron-35-bolt-74b-24gb: switch to the CARD's image path — docker-images/nemotron-bolt-b12x (thin FROM the card's stock vLLM nightly 77154ca by arm64 digest + b12x 1.5.1 + ultra_v3 parser plugin baked at /opt); recipe flags verbatim from the card incl. LiLiCorr dflash spec-decode (7) + ultra_v3 parser; only deviation GMU 0.92→0.90 (clean Spark reports 111.55/121.63 GiB free; 0.92 misses the boot gate by 0.35). eugr/spark-vllm-b12x (03a95654) does NOT carry LiLiCorrDraftModel/ultra_v3 — it cannot serve Bolt with the card's flags. Verified live: LiLiCorr speculator captured, smoke OK.
|
5 일 전 |
|
qwen38-flashnext-nvfp4
|
24a8341fad
docker-images: qwen38-flashnext-nvfp4
|
1 주 전 |
|
solar-open2-nvfp4
|
ad8fb377bf
docker-images: solar-open2-nvfp4
|
1 주 전 |
|
sparkring-shared
|
df46bb8b07
docker-images: sparkring-shared
|
1 주 전 |
Alexander Korolev
ec17b00796
dsv41-flash-1017-2x-tensorfold: ship it as an sm121 recipe