Drilldown: Recipe - CMP Wiki

Jump to content

Choose a table:

Recipe > decode tps: 140-160

Use the filters below to narrow your results.

DeepSeek V4.1 Flash heretic on 4x 8 GB (1) · DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Deepinfer-SM80 TP4 x PP2) (1) · Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3) (1)

DeepSeek-V4.1-Flash-1017 (2) · DeepSeek-V4.1-Flash-1017 heretic (pqhaz abliteration) (1) · Qwen3.8-Flash-Next (1)

EXL3 5.05 bpw; PLE (n-gram) table read from SSD (1) · Hybrid: LibertAI EXL3 2.9 bpw routed experts (layers 0-39), official FP8/FP4 for attention, shared experts, head, draft and Engram; KV fp8_ds_mla (1) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16 with the 38 heretic attn.wo_b tensors (1) · Official checkpoint (FP8 dense, FP4 experts); software FP8 on sm_80 (1)

Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · Morrowmake/vllm-cmp170hx (EXL3 path) (1) · Morrowmake/vllm-cmp170hx (vLLM fork, container image) (1) · vLLM PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules (1)

Deepinfer-SM80, vLLM v0.28.1rc0 base (1) · recipe 1.0.0 (commit d4d1f525), engine a0c57b52 (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)

8 GB (4)

2 (1) · 4 (2) · 8 (1)

TP2 with expert parallel (1) · TP4 (1) · TP4 x PP2, partition 20,20 (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1)

1,048,576 (1) · 262,144 (2) · 262,144 (weights address 1,048,576) (1)

144.2 (1) · 152.6 (1) · 153.35 (1) · 158 (1)

1,523 (1) · 2,453 (1) · 2,651 (1) · 3,463 (1)

64 GiB, --gpu-memory-utilization 0.92 (miner co-resident) (1) · 64 GiB, --gpu-memory-utilization 0.95 (2) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)

None (3) · 140 W (1)

None (4)

None (4)

Reported (4)

CurtisAccelerate (1) · darkmaniac7 (1) · HalfVulpes (1) · voidgiraffe (1)

October 16, 2026 (1) · October 22, 2026 (1) · October 28, 2026 (1) · October 29, 2026 (1)

https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (1) · https://github.com/HalfVulpes/Deepinfer-SM80 (1) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (1) · https://github.com/Morrowmake/qwen38-flash-next-cmp170hx-recipe (1)

Showing below up to 4 results in range #1 to #4.

Retrieved from "https://cmp.wiki/wiki/Special:Drilldown/Recipe"