| .. |
|
deepseek-v4-flash
|
ae1285dfdf
fix: reduce gpu-memory-utilization to 0.75 for deepseek-v4-flash
|
пре 3 месеци |
|
deepseek-v4-flash-dspark
|
7519fcef2a
chore(deepseek-v4-flash): disable temperature/top_p chat-template kwargs
|
пре 3 месеци |
|
gemma4-12b
|
5931869d69
refactor: DistributedBackend as Option — remove None_ variant
|
пре 4 месеци |
|
glm51
|
09841103d8
fix: default DistributedBackend to None_ (absent means single-node)
|
пре 4 месеци |
|
glm52
|
ef03b8c784
feat: auto-scale PP when pipeline_parallel_size == required_nodes
|
пре 4 месеци |
|
glm52-hybrid-fp8-mxfp4
|
67de1f34da
refactor(build): rename docker-images/glm52-int4-int8 to glm52
|
пре 2 месеци |
|
glm52-int4-int8
|
67de1f34da
refactor(build): rename docker-images/glm52-int4-int8 to glm52
|
пре 2 месеци |
|
glm52-mxfp4-experts-gptq
|
67de1f34da
refactor(build): rename docker-images/glm52-int4-int8 to glm52
|
пре 2 месеци |
|
glm52-nf3-hybrid-context
|
9e28b49887
feat(recipes): add volumes support and GLM-5.2 Hybrid FP8-MXFP4 recipe
|
пре 3 месеци |
|
glm52-nf3-hybrid-fast
|
9e28b49887
feat(recipes): add volumes support and GLM-5.2 Hybrid FP8-MXFP4 recipe
|
пре 3 месеци |
|
glm52-nf4-lloyd-experts-gptq
|
70ff8fda18
feat(recipe): add GLM-5.2 NF4 Lloyd-Experts-GPTQ recipe, bump glm52 image to 1.4
|
пре 2 месеци |
|
laguna-m1-nvfp4
|
e692ec1813
feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1
|
пре 3 месеци |
|
laguna-s2.1-nvfp4
|
d14021070c
feat(recipe): enable DFlash speculative decoding for Laguna S 2.1
|
пре 3 месеци |
|
mimo-v2.5-nvfp4
|
e692ec1813
feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1
|
пре 3 месеци |
|
minimax-m3
|
ef03b8c784
feat: auto-scale PP when pipeline_parallel_size == required_nodes
|
пре 4 месеци |
|
minimax-m3-mxfp8
|
227eb18915
feat: auto-set VLLM_LOGGING_COLOR=1 on head node (override via recipe [env])
|
пре 4 месеци |
|
minimax-m3-nvfp4
|
ef03b8c784
feat: auto-scale PP when pipeline_parallel_size == required_nodes
|
пре 4 месеци |
|
qwen-agentworld-35b
|
e692ec1813
feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1
|
пре 3 месеци |
|
solar-open2-nvfp4
|
febdc3b9d7
feat(build): add Solar Open2 NVFP4 recipe with recipe-pinned versions
|
пре 2 месеци |
|
test-mods
|
5931869d69
refactor: DistributedBackend as Option — remove None_ variant
|
пре 4 месеци |
|
test-sleep
|
1fa2811301
feat: default recipe port is 30000
|
пре 4 месеци |
Alexander Korolev
70ff8fda18
feat(recipe): add GLM-5.2 NF4 Lloyd-Experts-GPTQ recipe, bump glm52 image to 1.4