Alexander Korolev 5de97ee3aa fix(deepseek-v4): get DeepSeek-V4-Flash DSpark booting on production-3.8 (ds4) vor 2 Monaten
..
deepseek-v4-flash 5bc841f211 tmp: rename to simplify vor 2 Monaten
deepseek-v4-flash-dspark38 5de97ee3aa fix(deepseek-v4): get DeepSeek-V4-Flash DSpark booting on production-3.8 (ds4) vor 2 Monaten
deepseek-v4-flash-eugr d2026c2ddf feat(deepseek-v4): raise max-model-len to 1M + pin KV cache bytes (eugr) vor 2 Monaten
deepseek-v4-flash-eugr-agent 3aa9d380b2 feat(recipes): agent-serving profile + GMU/env fixes from benchmark findings vor 2 Monaten
deepseek-v4-flash-src 3aa9d380b2 feat(recipes): agent-serving profile + GMU/env fixes from benchmark findings vor 2 Monaten
gemma4-12b 5931869d69 refactor: DistributedBackend as Option — remove None_ variant vor 4 Monaten
glm51 09841103d8 fix: default DistributedBackend to None_ (absent means single-node) vor 4 Monaten
glm52 ef03b8c784 feat: auto-scale PP when pipeline_parallel_size == required_nodes vor 4 Monaten
glm52-hybrid-fp8-mxfp4 67de1f34da refactor(build): rename docker-images/glm52-int4-int8 to glm52 vor 2 Monaten
glm52-int4-int8 67de1f34da refactor(build): rename docker-images/glm52-int4-int8 to glm52 vor 2 Monaten
glm52-mxfp4-experts-gptq 67de1f34da refactor(build): rename docker-images/glm52-int4-int8 to glm52 vor 2 Monaten
glm52-nf3-hybrid-context 9e28b49887 feat(recipes): add volumes support and GLM-5.2 Hybrid FP8-MXFP4 recipe vor 3 Monaten
glm52-nf3-hybrid-fast 9e28b49887 feat(recipes): add volumes support and GLM-5.2 Hybrid FP8-MXFP4 recipe vor 3 Monaten
glm52-nf4-lloyd-experts-gptq 240002c125 fix(glm52): patch vLLM structured-output reasoning-boundary bug under MTP vor 2 Monaten
laguna-m1-nvfp4 e692ec1813 feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1 vor 3 Monaten
laguna-s2.1-nvfp4 a3bd00eef8 fix: tmux serve quoting, venv setup, cluster probe on dgx3.lan vor 2 Monaten
mimo-v2.5-nvfp4 e692ec1813 feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1 vor 3 Monaten
minimax-m3 ef03b8c784 feat: auto-scale PP when pipeline_parallel_size == required_nodes vor 4 Monaten
minimax-m3-mxfp8 227eb18915 feat: auto-set VLLM_LOGGING_COLOR=1 on head node (override via recipe [env]) vor 4 Monaten
minimax-m3-nvfp4 ef03b8c784 feat: auto-scale PP when pipeline_parallel_size == required_nodes vor 4 Monaten
qwen-agentworld-35b e692ec1813 feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1 vor 3 Monaten
solar-open2-nvfp4 0816b7ad25 fix(recipe): change solar-open2 served-model-name to solar vor 2 Monaten
test-composed 0208fc12f1 feat(compose): support subdirectory globs in composed_model sources vor 2 Monaten
test-mods 5931869d69 refactor: DistributedBackend as Option — remove None_ variant vor 4 Monaten
test-sleep 1fa2811301 feat: default recipe port is 30000 vor 4 Monaten