Alexander Korolev 75a7055af5 feat(glm52): build on production-hybrid-1.3 base with pinned deps 3 miesięcy temu
..
deepseek-v4-flash ae1285dfdf fix: reduce gpu-memory-utilization to 0.75 for deepseek-v4-flash 3 miesięcy temu
deepseek-v4-flash-dspark 57d686b17b fix(deepseek-v4): add NCCL ABI fix + instanttensor overlay image 3 miesięcy temu
gemma4-12b 5931869d69 refactor: DistributedBackend as Option — remove None_ variant 4 miesięcy temu
glm51 09841103d8 fix: default DistributedBackend to None_ (absent means single-node) 4 miesięcy temu
glm52 ef03b8c784 feat: auto-scale PP when pipeline_parallel_size == required_nodes 4 miesięcy temu
glm52-hybrid-fp8-mxfp4 75a7055af5 feat(glm52): build on production-hybrid-1.3 base with pinned deps 3 miesięcy temu
glm52-int4-int8 9e28b49887 feat(recipes): add volumes support and GLM-5.2 Hybrid FP8-MXFP4 recipe 3 miesięcy temu
glm52-nf3-hybrid-context 9e28b49887 feat(recipes): add volumes support and GLM-5.2 Hybrid FP8-MXFP4 recipe 3 miesięcy temu
glm52-nf3-hybrid-fast 9e28b49887 feat(recipes): add volumes support and GLM-5.2 Hybrid FP8-MXFP4 recipe 3 miesięcy temu
laguna-m1-nvfp4 e692ec1813 feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1 3 miesięcy temu
laguna-s2.1-nvfp4 d14021070c feat(recipe): enable DFlash speculative decoding for Laguna S 2.1 3 miesięcy temu
mimo-v2.5-nvfp4 e692ec1813 feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1 3 miesięcy temu
minimax-m3 ef03b8c784 feat: auto-scale PP when pipeline_parallel_size == required_nodes 4 miesięcy temu
minimax-m3-mxfp8 227eb18915 feat: auto-set VLLM_LOGGING_COLOR=1 on head node (override via recipe [env]) 4 miesięcy temu
minimax-m3-nvfp4 ef03b8c784 feat: auto-scale PP when pipeline_parallel_size == required_nodes 4 miesięcy temu
qwen-agentworld-35b e692ec1813 feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1 3 miesięcy temu
test-mods 5931869d69 refactor: DistributedBackend as Option — remove None_ variant 4 miesięcy temu
test-sleep 1fa2811301 feat: default recipe port is 30000 4 miesięcy temu