Drilldown: Recipe
More actions
Recipe > decode tps:
161-260 
& source :
https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe or
Other
& source :
https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe or
Other Use the filters below to narrow your results.
page:
model:
quant:
AWQ W4A16 g32 (leoncca/Qwen3.8-Flash-Next-Uncensored-AWQ-g32); PLE table converted to INT4 and served from SSD (1) ·
Hybrid: routed experts EXL3 (mostly 3 bpw, 2 bpw on layers 18-22) from LibertAI's 2.9 bpw pack; attention, shared experts, indexer and DSpark drafter official FP8; KV fp8_ds_mla (1) ·
Mixed INT4 AutoRound (Minachist/Qwen3.8-Flash-Next-INT4-Mixed-AutoRound, about 65 GB) with the full BF16 PLE table on NVMe (1) ·
NVFP4 main weights through Marlin (no native FP4 on sm_80), mixed FP8 and BF16 MTP weights, FP8 PLE table (about 51.2 GB) kept on NVMe (1) ·
W4A16 (INT4 weights, Marlin kernels) (1)
engine:
Qwen-Flash-SM80 overlay on vllm/vllm-openai:qwen38-flash-next (digest-pinned), FlashInfer PCIe IPC AllReduce, GDS/cuFile over NVMe P2PDMA (1) ·
vLLM (1) ·
vLLM 0.29.1rc1 nightly plus the checkpoint author's patches (1) ·
vLLM with a pinned sm_80 patch stack (built locally from source) (1) ·
wtdcode/vllm-backport 3142ded1 plus a two-file patch and two tinybeast PLE plugins (venv, no container) (1)
engine version:
cards:
topology:
context:
decode tps:
prefill tps:
vram per card:
power cap:
driver:
unlock build:
status:
tested by:
tested on:
source: (Click arrow to add another value)
Showing below up to 5 results in range #1 to #5.