Drilldown: Recipe
More actions
Recipe > decode tps:
160-180 
& source :
https://github.com/Morrowmake/glm53-flash-cmp170hx-recipe or
Other
& source :
https://github.com/Morrowmake/glm53-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) ·
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) ·
Official checkpoint (FP8 dense, FP4 experts); software FP8 on sm_80 (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 PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules (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:
driver:
unlock build:
status:
tested by:
tested on:
source: (Click arrow to add another value)
Showing below up to 4 results in range #1 to #4.