Serving recipe for the abliterated (refusal-suppressed) GLM-5.2 with a true 4-bit NVFP4 KV cache on a 4-node DGX Spark cluster (GB10, sm_121), vLLM TP=4, MTP k=5. GLM-5.2-NVFP4-KV-4x-DGX-Spark-300kctx ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results