GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K context, DeepSeek Sparse Attention + MTP speculative decode
Python Updated 5 months ago 1 commits 17 stars
vortex-ai|Mirror: 0xSero/glm-5.2-sm120 (⭐17)
5 months agoE2B SandboxFirecracker microVMpython
No executable code files found in this repository.
About
GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K context, DeepSeek Sparse Attention + MTP speculative decode
Readme
17 stars
2 forks