Drilldown: Recipe
More actions
Use the filters below to narrow your results.
page:
DeepSeek V4 Flash 0731 on 4x 8 GB (allover326 PP4 DSpark) (1) ·
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 5x 8 GB (PP5 full residency) (1) ·
DeepSeek V4.1 Flash on 6x 8 GB (Deepinfer-SM80 TP2 x PP3) (1) ·
DeepSeek V4.1 Flash on 6x 8 GB (TP6) (1) ·
DeepSeek V4.1 Flash on 8x 8 GB (Deepinfer-SM80 TP4 x PP2) (1) ·
DeepSeek V4.1 Flash on 8x 8 GB (Zanooda PP8) (1) ·
GLM 5.3 Flash on 3x 8 GB (1) ·
GLM 5.3 Flash on 8x 8 GB (promisezackr PP8 NVFP4 DFlash2) (1) ·
GLM 5.3 on 8x 8 GB (Int4-Int8Mix PP8) (1) ·
GLM 5.3 on 8x 8 GB (vllm-170hx-glm5) (1) ·
Qwen3.8 Flash Next on 3x 8 GB (clee PP3) (1) ·
Qwen3.8 Flash Next on 3x or 4x 8 GB (zebgop-ops FP8 PP) (1) ·
Qwen3.8 Flash Next on 4x 8 GB (1)
model:
DeepSeek-V4-Flash-0731 (1) ·
DeepSeek-V4.1-Flash (1) ·
DeepSeek-V4.1-Flash-1017 (5) ·
DeepSeek-V4.1-Flash-1017 heretic (pqhaz abliteration) (1) ·
GLM-5.3 (full 78-layer DSA MoE, not Flash) (1) ·
GLM-5.3 (full 78-layer, not Flash) (1) ·
GLM-5.3-Flash (1) ·
GLM-5.3-Flash (320B MoE, 18B active) (1) ·
Qwen/Qwen3.8-Flash-Next-FP8 (revision bcd9f01d) (1) ·
Qwen3.8-Flash-Next (2)
quant:
AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (1) ·
GLM-5.3-Int4-Int8Mix (INT4 / INT8 mix); KV fp8_ds_mla (1) ·
GLM-5.3-Int4-Int8Mix-AWQ-g64; drafter incoai/GLM-5.3-DFlash2 (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) ·
LibertAIDAI/GLM-5.3-Flash-NVFP4 (ModelOpt NVFP4, routed experts only, 181 GiB), run through Marlin W4A16 kernels; GLM-5.3-Flash DFlash2 drafter (5 sliding-window layers) (1) ·
Native MXFP4 experts + FP8 attention (official deepseek-ai checkpoint, about 155.4 GiB); KV cache fp8 (1) ·
Official block FP8, about 126 GiB including the about 50 GiB FP8 n-gram (PLE) table, which is served from host RAM; KV cache bf16 (the QSA layers refuse fp8) (1) ·
Official checkpoint (510 GB: MXFP4 routed experts, FP8 dense layers, 203 GB FP8 Engram table); KV cache fp8_ds_mla (1) ·
Official checkpoint (FP8 dense, FP4 experts); software FP8 on sm_80 (2) ·
Official checkpoint as downloaded: MXFP4 routed experts as Marlin W4A16, MXFP8 dense as Marlin W8A16; KV fp8 (1) ·
Official checkpoint: dense MXFP8 through an SM80 Marlin W8A16 path, routed experts MXFP4 through W4A16; KV FP8 (1) ·
W4A16 AutoRound: Intel/Qwen3.8-Flash-Next-W4A16-AutoRound; 95.4 GiB BF16 PLE table streamed from NVMe; KV fp8 e4m3 (software-decoded on SM80) (1) ·
W4A16, about 4.3 bpw, 163 GiB on disk (1)
engine:
Custom SM80 vLLM (patched from public commit 79a7108d9) (1) ·
Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) ·
Morrowmake/vllm-cmp170hx (via the glm53-flash-cmp170hx-recipe) (1) ·
Morrowmake/vllm-cmp170hx (vLLM fork, container image) (1) ·
Morrowmake/vllm-cmp170hx branch ampere-glm53 plus fail-closed source patches (1) ·
vLLM (build not stated) (1) ·
vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) (1) ·
vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 (1) ·
vLLM PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules (2) ·
vLLM: 344303947's fork of wtdcode/vllm-backport (shadow source layer, staged Marlin repack, exact-size Engram pinning) (1) ·
vLLM: haosdent/vllm branch dsv4-flash-a100 plus allover326's 7 patches (DSpark under PP, sm_80 prefill top-k fallback, logits row chunking) (1) ·
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) (1) ·
vLLM: the vllm/vllm-openai:qwen38-flash-next image with zebgop-ops patches 0001 to 0016 (never 0008-WITHDRAWN) and three ported files (1) ·
wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) (1)
engine version:
None (1) ·
0.1.dev20073+g8e685d198; repo commit 2f551bb (patch 0016, 2026-10-02) (1) ·
base c3046d1 (recommended since 2026-08-13; first released on f8ea5bb); repo commit 3dd2d88 (1) ·
Deepinfer-SM80 2a828fc lineage; vLLM v0.28.1rc0 base (1) ·
Deepinfer-SM80, vLLM v0.28.1rc0 base (1) ·
latest-sm80 tag as of 2026-10-16 (1) ·
not stated (1) ·
q38fn/stack on nightly-7d0b4e57 (1) ·
recipe 1.0.0 (commit d4d1f525), engine a0c57b52 (1) ·
recipe 31318fd; patches 0001-0020 (1) ·
reports 0.0.0; patches/public-base-to-runtime.patch (109 files) (1) ·
v0.1.dev20051+g487ecf187 (the image's vLLM); repo commit 90ec72e (1) ·
v0.13.1.dev6, tag v41-pp5-1m-pinmem-20260916 (1) ·
vLLM 0.30.1rc1, fork commit 378c37b0 (1) ·
vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)
cards:
topology:
PP3 (1) ·
PP3, no P2P (works at PP2 on two cards) (1) ·
PP4 (VLLM_PP_LAYER_PARTITION=12,12,12,7) with DSpark, 5 draft tokens; PCIe Gen2 x4, no P2P (1) ·
PP4, VLLM_PP_LAYER_PARTITION=12,12,12,12, MTP 3, FULL_AND_PIECEWISE CUDA graphs; PCIe Gen2 x4 per card, no P2P. Three cards: PP3 with 16,17,15 or 16,16,16 (1) ·
PP5 with an even 8,8,8,8,8 layer split; the repo's cards are on PCIe Gen2 x16 with no NVLink (1) ·
PP8 (also PP9 and PP10), TP1 (1) ·
PP8 (VLLM_PP_LAYER_PARTITION=7,5,7,5,7,5,7,2) with DFlash2, 7 draft tokens; PCIe Gen2 x4, no P2P; host 2x Xeon E5-2690 v4, 96 GB DDR4 (1) ·
PP8, partition 5,5,5,5,5,5,5,5 (1) ·
PP8, TP1 (1) ·
TP2 x PP3, partition 14,14,12 (1) ·
TP4 (1) ·
TP4 with expert parallel, MTP 3 (1) ·
TP4 x PP2, partition 20,20 (1) ·
TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1) ·
TP6 (virtual-head padding), PP1 (1)
context:
1,000,000 (YaRN x4 from 262,144) (1) ·
1,047,736 verified one-shot; 1,002,852 over a 405-turn chat with DSV4_LOGITS_ROW_CHUNK=64 (1) ·
1,048,576 (5) ·
1,048,576 (KV pool 1,632,827 tokens at utilisation 0.97; an 896K-token prompt passed) (1) ·
1,048,576 (KV pool 6.62M tokens at utilization 0.90, about 6.3 concurrent 1M requests) (1) ·
1,048,576 (YaRN x4) (1) ·
1,048,576 per request (1) ·
262,144 (1) ·
262,144 (weights address 1,048,576) (1) ·
262,144 native; 524,288 with YaRN 2.0; 1,048,576 with YaRN 4.0 (needle verified on PP3) (1) ·
about 1,000,000 (8-bit KV cache) (1)
decode tps:
prefill tps:
vram per card:
64 GB (1) ·
64 GB, --gpu-memory-utilization 0.85 (1) ·
64 GB, --gpu-memory-utilization 0.90 (1) ·
64 GB, --gpu-memory-utilization 0.95 (1) ·
64 GB, full residency (no expert offload), --gpu-memory-utilization 0.97 (1) ·
64 GB; weights 35.9 GB per rank (ranks 1-6), 37.6 GB rank 0, 46.3 GB rank 7 (1) ·
64 GiB (2) ·
64 GiB, --gpu-memory-utilization 0.92 (miner co-resident) (1) ·
64 GiB, --gpu-memory-utilization 0.95 (1) ·
64 GiB, --gpu-memory-utilization 0.97 (1) ·
64 GiB, gpu-memory-utilization 0.92 (1) ·
64 GiB, GPU_UTIL 0.96 at PP8 (1) ·
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 (1) ·
about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)
power cap:
driver: (Click arrow to add another value)
unlock build:
status:
tested by:
tested on:
source:
https://discord.com/channels/1518634379604136178/1518695289278566450/1561743826945843304 (1) ·
https://discord.com/channels/1518634379604136178/1528826330454429706/1557523316120748073 (1) ·
https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (1) ·
https://github.com/344303947/dsv41-flash-pp5-170hx (1) ·
https://github.com/allover326/deepseek-v4-cmp170hx (1) ·
https://github.com/arvkmr/vllm-170hx-glm5 (1) ·
https://github.com/clee/qwen3.8-flash-next-3x170hx (1) ·
https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (1) ·
https://github.com/HalfVulpes/Deepinfer-SM80 (2) ·
https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (1) ·
https://github.com/promisezackr/glm53-flash-170hx-pp8 (1) ·
https://github.com/wgkbfcp/deepseek-v4.1-flash-1017-cmp170hx-recipe (1) ·
https://github.com/Zanooda/deepseek-v4.1-flash-cmp170hx (1) ·
https://github.com/zebgop-ops/qwen38-flashnext-pp (1)
Showing below up to 15 results in range #1 to #15.