b9521

(llama.cpp) ➜  llama.cpp git:(master) ✗ python mtp-bench.py
  code_python        pred= 192 draft= 150 acc= 116 rate=0.773 tok/s=202.8
  code_cpp           pred= 192 draft= 147 acc= 117 rate=0.796 tok/s=212.8
  explain_concept    pred= 192 draft= 161 acc= 110 rate=0.683 tok/s=196.4
  summarize          pred= 192 draft= 138 acc= 122 rate=0.884 tok/s=226.6
  qa_factual         pred= 192 draft= 138 acc= 121 rate=0.877 tok/s=225.1
  translation        pred= 192 draft= 158 acc= 112 rate=0.709 tok/s=201.5
  creative_short     pred= 192 draft= 160 acc= 110 rate=0.688 tok/s=197.2
  stepwise_math      pred= 192 draft= 150 acc= 115 rate=0.767 tok/s=209.2
  long_code_review   pred= 192 draft= 148 acc= 116 rate=0.784 tok/s=208.9

(llama.cpp) ➜  llama.cpp git:(master) ✗ python mtp-bench.py
  code_python        pred= 192 draft= 150 acc= 116 rate=0.773 tok/s=211.9
  code_cpp           pred= 192 draft= 147 acc= 117 rate=0.796 tok/s=224.6
  explain_concept    pred= 192 draft= 161 acc= 110 rate=0.683 tok/s=207.8
  summarize          pred= 192 draft= 138 acc= 122 rate=0.884 tok/s=240.2
  qa_factual         pred= 192 draft= 138 acc= 121 rate=0.877 tok/s=238.5
  translation        pred= 192 draft= 158 acc= 112 rate=0.709 tok/s=213.4
  creative_short     pred= 192 draft= 160 acc= 110 rate=0.688 tok/s=208.8
  stepwise_math      pred= 192 draft= 150 acc= 115 rate=0.767 tok/s=221.7
  long_code_review   pred= 192 draft= 148 acc= 116 rate=0.784 tok/s=220.7

➜  llama.cpp git:(osimons/enroll_mul_mat_vec_q_moe_into_PDL) ✗ ./build-x64-linux-gcc-reldbg/bin/llama-server \
    -m /mnt/share/gguf/unsloth/Qwen3.6-35B-A3B-MTP-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf -dio \
    --spec-type draft-mtp \
    --spec-draft-n-max 2 \
    -ngl all \
    -fa on \
    --host 0.0.0.0 \
    --port 8080 -np 1 --chat-template-kwargs "{\"preserve_thinking\": true}"