| .. |
|
deepseek-v4-flash-dspark
|
5a9795c612
Rebase deepseek-v4-flash :fixed overlay onto production-3.76.1
|
hai 2 meses |
|
deepseek-v4-flash-dspark-src
|
1bae27bd44
fix(docker): complete DS4 src runtime lock with flashinfer transitive deps
|
hai 2 meses |
|
deepseek-v4-flash-dspark38
|
25b18fcd56
fix(deepseek-v4): drafter b12x WO routing for real DSpark acceptance + GMU 0.78
|
hai 2 meses |
|
deepseek-v4-flash-eugr
|
7742fbf290
feat(deepseek-v4-flash): fix current parameters
|
hai 1 mes |
|
glm52
|
240002c125
fix(glm52): patch vLLM structured-output reasoning-boundary bug under MTP
|
hai 2 meses |
|
glm52-nf3-hybrid
|
febdc3b9d7
feat(build): add Solar Open2 NVFP4 recipe with recipe-pinned versions
|
hai 2 meses |
|
glm53-flash-dflash2
|
1c1d3455f8
glm53-flash: NVFP4-4p67 + DFlash2-MXFP8 recipes (model cards followed, GB10-adapted)
|
hai 1 mes |
|
glm53-flash-nvfp4
|
ed4e0f99ea
build(images): digest-pin glm53 base image — tag glm53-flash-arm64-cu130 is mutable; pin sha256:905c0293 (the base our verified images were built on). Checksum changes → one no-op rebuild on next serve.
|
hai 1 mes |
|
glm53-flash-nvfp4-lab
|
ed4e0f99ea
build(images): digest-pin glm53 base image — tag glm53-flash-arm64-cu130 is mutable; pin sha256:905c0293 (the base our verified images were built on). Checksum changes → one no-op rebuild on next serve.
|
hai 1 mes |
|
qwen38-flashnext-nvfp4
|
5ee2326c40
fix(recipes): switch Qwen3.8-Flash-Next to NVFP4 for 2x Spark
|
hai 1 mes |
|
solar-open2-nvfp4
|
febdc3b9d7
feat(build): add Solar Open2 NVFP4 recipe with recipe-pinned versions
|
hai 2 meses |
Alexander Korolev
1c1d3455f8
glm53-flash: NVFP4-4p67 + DFlash2-MXFP8 recipes (model cards followed, GB10-adapted)