Use the filters below to narrow your results.
page:
(There are no values for this filter)
model:
(There are no values for this filter)
quant:
(There are no values for this filter)
engine:
(Click arrow to add another value)
Morrowmake/vllm-cmp170hx (vLLM fork, container image) ·
vLLM PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules ·
Custom SM80 vLLM (patched from public commit 79a7108d9) ·
ExLlamaV3 (patched, pinned) ·
ExLlamaV3 1.5.4 (built for SM80) with a small OpenAI-compatible server ·
ExLlamaV3 fork (anoane/exllamav3-anemone) + TabbyAPI fork (anoane/tabbyAPI) ·
GNmac-lab recipe image 1.2.0 (vLLM with sm_80 patches) plus three patches ·
Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels ·
Morrowmake/vllm-cmp170hx (EXL3 path) ·
Morrowmake/vllm-cmp170hx (via the glm53-flash-cmp170hx-recipe) ·
Morrowmake/vllm-cmp170hx branch ampere-glm53 plus fail-closed source patches ·
Morrowmake/vllm-cmp170hx image (Qwen EXL3 release) with patch files mounted read-only ·
Morrowmake/vllm-cmp170hx image (tag qwen38-recipe-1.0.0) plus one mounted file (vLLM #58235 vision-sink fix) ·
Morrowmake/vllm-cmp170hx image with patch files mounted read-only ·
Project Maya (Strata and llama.cpp lineage) ·
Project Maya (Strata and llama.cpp lineage, EXL3 loading, DFlash2 drafter) ·
Qwen-Flash-SM80 overlay on vllm/vllm-openai:qwen38-flash-next (digest-pinned), FlashInfer PCIe IPC AllReduce, GDS/cuFile over NVMe P2PDMA ·
vLLM ·
vLLM (build not stated) ·
vLLM 0.29.1rc1 nightly plus the checkpoint author's patches ·
vLLM a5a30471 plus a 13-file downstream patch (native Linux AIO PLE reader) ·
vLLM nightly + PR #53899 (a5530b9) + the repo's patch scripts ·
vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) ·
vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 ·
vLLM v0.30.0 + zankich INT4-PLE plugin + six hash-guarded patch layers ·
vLLM with a pinned sm_80 patch stack (built locally from source) ·
vLLM: 344303947's fork of wtdcode/vllm-backport (shadow source layer, staged Marlin repack, exact-size Engram pinning) ·
vLLM: haosdent/vllm branch dsv4-flash-a100 plus allover326's 7 patches (DSpark under PP, sm_80 prefill top-k fallback, logits row chunking) ·
vLLM: haosdent/vllm branch dsv4-flash-a100 with a vendored copy of allover326's 7 patches (image dsv4-a100:devel) ·
vLLM: hyd998877/vllm_170hx_glm53-flash-exl3-optimized with kaka86mm's overlay patches; exllamav3 1.4.8 ·
vLLM: official vllm/vllm-openai:glm53-flash image plus promisezackr's 24 patches (SM8x base from 344303947/vllm170hx, pipeline parallel for GLM-5.3-Flash, DFlash2 under PP8) ·
vLLM: the vllm/vllm-openai:qwen38-flash-next image with zebgop-ops patches 0001 to 0016 (never 0008-WITHDRAWN) and three ported files ·
wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) ·
wtdcode/vllm-backport 3142ded1 plus a two-file patch and two tinybeast PLE plugins (venv, no container) ·
Other ·
None
engine version:
(There are no values for this filter)
cards:
(There are no values for this filter)
card count:
(There are no values for this filter)
topology:
(There are no values for this filter)
context:
(There are no values for this filter)
decode tps:
(There are no values for this filter)
prefill tps:
(There are no values for this filter)
vram per card:
(Click arrow to add another value)
64 GB ·
64 GiB ·
64 GiB exposed, --gpu-memory-utilization 0.95 ·
64 GiB, --gpu-memory-utilization 0.95 ·
64 GB (65,536 MiB), --gpu-memory-utilization 0.965 ·
64 GB, --gpu-memory-utilization 0.85 ·
64 GB, --gpu-memory-utilization 0.90 ·
64 GB, --gpu-memory-utilization 0.93 (0.94 is the ceiling) ·
64 GB, --gpu-memory-utilization 0.93 (v0.3.0) ·
64 GB, --gpu-memory-utilization 0.94, TB_TORCH_MEM_CAP_GIB=61.5 ·
64 GB, --gpu-memory-utilization 0.95 ·
64 GB, full residency (no expert offload), --gpu-memory-utilization 0.97 ·
64 GB; weights 35.9 GB per rank (ranks 1-6), 37.6 GB rank 0, 46.3 GB rank 7 ·
64 GiB (64,911 MiB usable), GPU_MEMORY_UTILIZATION 0.98 ·
64 GiB, --gpu-memory-utilization 0.90 ·
64 GiB, --gpu-memory-utilization 0.92 (miner co-resident) ·
64 GiB, --gpu-memory-utilization 0.95 (fixed) ·
64 GiB, --gpu-memory-utilization 0.96 ·
64 GiB, --gpu-memory-utilization 0.97 ·
64 GiB, gpu-memory-utilization 0.92 ·
64 GiB, GPU_MEMORY_UTILIZATION 0.95 ·
64 GiB, GPU_UTIL 0.95 (fixed) ·
64 GiB, GPU_UTIL 0.96 at PP8 ·
64 GiB; --gpu-memory-utilization 0.94 plus per-rank KV budgets; measured 34.0-34.3 GiB per 12-layer rank, 37.9 GiB on the drafter rank ·
64 GiB; weights 45.5 GiB plus 10 GiB KV per card; GPU_UTIL 0.94 (fixed) ·
64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 ·
about 58 GiB of 64 GiB (116.6 GiB resident across both) ·
about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 ·
about 62.9 / 62.3 GiB idle, peaks about 64.4 / 63.0 GiB with vision ·
gpu_split 58 GB per CMP, 70 GB on the PRO ·
Other ·
None
power cap:
(There are no values for this filter)
driver:
(There are no values for this filter)
unlock build:
(There are no values for this filter)
status:
(Click arrow to add another value)
tested by:
(There are no values for this filter)
tested on:
(There are no values for this filter)
source:
(There are no values for this filter)
There are no results for this report.
