Kimi-K2.5 via KTransformers+SGLang on a hybrid GPU/CPU memory offload config: 4x RTX Pro 6000 Blackwells + 640GB RAM The original baseline was on 8x GPUs using a synthetic coding agent style workload targeting 2k-45k input tokens, 80-3k max output tokens, and with up to 10 concurrent requests. Re-ran on the new hybrid setup The best I could get: - 23.03 output tokens/s @ 10 concurrent requests - Mean TTFT: ~60s - Median TTFT: ~64s Baseline results: - 74.39 output tokens/s @ 10 concurrent requests - Mean TTFT: ~9s - Median TTFT: ~3.7s

Full command: export CUDA_VISIBLE_DEVICES=0,1,2,3 export OMP_NUM_THREADS=1 export MKL_NUM_THREADS=1 export OPENBLAS_NUM_THREADS=1 export NUMEXPR_NUM_THREADS=1 export VECLIB_MAXIMUM_THREADS=1 export PYTHONUNBUFFERED=1 exec python -m sglang.launch_server \ --model-path /workspace/models/huggingface/models--moonshotai--Kimi-K2.5/snapshots/54383e83fa343a1331754112fb9e3410c55efa2f \ --kt-weight-path /workspace/models/huggingface/models--moonshotai--Kimi-K2.5/snapshots/54383e83fa343a1331754112fb9e3410c55efa2f \ --kt-threadpool-count 1 \ --kt-method RAWINT4 \ --trust-remote-code \ --served-model-name kimi_k2 \ --tool-call-parser kimi_k2 \ --reasoning-parser kimi_k2 \ --disable-radix-cache \ --disable-chunked-prefix-cache \ --tensor-parallel-size 4 \ --enable-p2p-check \ --disable-shared-experts-fusion \ --disable-cuda-graph \ --host 0.0.0.0 \ --port 8000 \ --kt-cpuinfer 32 \ --kt-num-gpu-experts 128 \ --kt-max-deferred-experts-per-token 2 \ --kt-gpu-prefill-token-threshold 1024 \ --kt-expert-placement-strategy uniform \ --mem-fraction-static 0.92 \ --enable-mixed-chunk \ --chunked-prefill-size 32658 \ --max-total-tokens 200000 \ --attention-backend flashinfer