Jump to content
Toggle search
Toggle menu
CMP Wiki
Toggle preferences menu
Toggle personal menu
Not logged in
Your IP address will be publicly visible if you make any edits.

Drilldown: Recipe

More actions
Recipe > card count: 2-4 & decode tps: 110-150 & status: Reported

Use the filters below to narrow your results.

page:
DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) (1) · Qwen3.8 Flash Next on 2x 8 GB (DUFRelic PP2) (1) · Qwen3.8 Flash Next on 4x 8 GB (1)
model:
DeepSeek-V4.1-Flash-1017 (1) · Qwen3.8-Flash-Next (2)
quant:
AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (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) · W4A16 INT4 g128 with the PLE table repacked INT4 g32: zankich/Qwen3.8-Flash-Next-W4A16-Merlin-INT4PLE-FP8KV; KV BF16 (1)
engine:
Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · vLLM v0.30.0 + zankich INT4-PLE plugin + six hash-guarded patch layers (1) · wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) (1)
engine version:
latest-sm80 tag as of 2026-10-16 (1) · vLLM v0.30.0 (ced6857a); plugin zankich/vllm v0.29.0z (6609bfef) (1) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)
cards:
8 GB (3)
card count:
2 (1) · 4 (2)
topology:
PP2, MTP depth 3 (1) · TP4 with expert parallel, MTP 3 (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1)
context:
1,000,000 (YaRN x4 from 262,144) (1) · 262,144 (1) · 262,144 (weights address 1,048,576) (1)
decode tps:
116.49 (1) · 133.39 (1) · 144.2 (1)
prefill tps:
1,523 (1) · 2,101.4 (1) · 6,213.66 (1)
vram per card:
64 GB (1) · 64 GiB, --gpu-memory-utilization 0.90 (1) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)
power cap:
None (1) · 140 W (1) · 140 W (200 W observed-draw abort guard) (1)
driver:
None (2) · NVIDIA 610.43.02 (1)
unlock build:
None (2) · amoghmunikote/cmpunlocker 6c442eeb (patch 0016 SM reconfig, 74 SMs) plus Bayley P2P patches 0011/0013/0015 (1)
status: (Click arrow to add another value)
tested by:
CurtisAccelerate (1) · dufrelic (1) · matstatman (1)
tested on:
October 3, 2026 (1) · October 16, 2026 (1) · October 22, 2026 (1)
source:
https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (1) · https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (1) · https://github.com/DUFRelic/qwen38-flash-next-recipe (1)

Showing below up to 3 results in range #1 to #3.

View (previous 250 | next 250) (20 | 50 | 100 | 250 | 500)


View (previous 250 | next 250) (20 | 50 | 100 | 250 | 500)

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