{"meta":{"count":2,"page":1,"pages":1,"per_page":12,"applied":{"engine":null,"model":null,"quant":null,"storage":null,"hardware":["rtx-4090","170hx-x6"],"generation":null,"task":null,"tier":null,"tags":[],"vram":null,"search":null,"sort":"updated","featured":false},"origin":"https://localairecipes.com","openapi":"/openapi.json","updated_at":"2026-11-03T20:24:11+00:00"},"recipes":[{"slug":"qwen3-8-flash-next-iq3-s-mtp-on-1x-rtx-4090-llama-cpp-tandem-cpp","title":"Qwen3.8-Flash-Next IQ3_S + MTP on 1x RTX 4090 \u2014 llama.cpp + tandem.cpp MoE expert cache (ewhacc)","summary":"MoE expert-cache offload for llama.cpp via the tandem.cpp patch set: hot experts stay in a GPU expert cache, missed experts are split between CPU compute and an upload into the cache, sized from measured CPU and PCIe speeds; single-user decode is the target. Author's GSM8K first-200 decode numbers on the consumer PC (i5-12400F, 64 GB DDR4, RTX 4090 24 GB): Qwen3.8-Flash-Next IQ3_S + MTP 97.3 tok/s greedy and 96.1 sampled vs llama.cpp f5222f25c 29.8/29.4 (3.3x); gpt-oss-120b 51.5/48.0. REPRO CAVEAT: all numbers are author-self-reported on a repo <24h old with one commit day of history (initial commit 2026-11-02, no releases/tags); nothing reproduced on-box or by a third party - evidence is claimed, tier community. Requires CUDA 13.0-13.4 on Linux (sm_89/sm_120) and 64 GB host RAM for the 78 GiB IQ3_S weights; 1.4-2.1x gains on other MoE models that don't fit VRAM.","tier":"community","beta":false,"generation":"ada","decode_tok_s":73.7999999999999971578290569595992565155029296875,"prefill_tok_s":0,"updated_at":"2026-11-02 09:53:20.10132-07","commit_sha":"543df76dcb783c7c365b8ea88a2d81ed9d36de76","content_hash":"fd8e878ab3aa782deec1708f8b0913a0ee5ea7a7","votes":0,"credit":[{"name":"ewhacc - recipe, patch set and measurements","url":"https://github.com/ewhacc/tandem.cpp"},{"name":"llama.cpp / ggml (MIT)","url":"https://github.com/ggml-org/llama.cpp"},{"name":"MoE expert-split rule adapted from Strata (Niko1221)","url":"https://github.com/Niko1221/Strata"}],"uploaded_by":"localai-recipes","measured":null,"links":{"self":"/api/v1/recipes/qwen3-8-flash-next-iq3-s-mtp-on-1x-rtx-4090-llama-cpp-tandem-cpp.json","alternate":"/r/qwen3-8-flash-next-iq3-s-mtp-on-1x-rtx-4090-llama-cpp-tandem-cpp"}},{"slug":"deepseek-v4-1-flash-sm80-deepinfer-kernel-port-6x-a100-dspark-k5","title":"DeepSeek-V4.1-Flash SM80 DeepInfer kernel port 6x CMP 170HX DSpark K5","summary":"DeepSeek-V4.1-Flash served on six 64 GB SM80 GPUs (GA100 die, owner-classified 170HX) with HalfVulpes' Deepinfer-SM80 patch set: a 30-file vLLM V1 overlay porting DeepSeek's DeepInfer kernel architecture (SM100 tcgen05/TMEM) to Ampere mma.sync tensor cores - unified 512-dim SM80 sparse-MLA decode/prefill kernels with bitshift UE8M0 scale decoding, a bit-exact single-CTA Triton TopK+SWA combiner (22.17x), direct-store KV-cache gather (7.64x @48K), SM80-aligned TileLang mHC routing (2.89x), and YOCO L20-L39 ragged indexer-metadata reuse (19 redundant kernel chains eliminated per chunk). TP2 x PP3 (14/14/12) + DSpark K=5 + 1M context, 4.65M-token GPU-resident KV. Author-measured: 64K cold prefill 4,507 tok/s (+24.2% vs baseline vLLM SM80), 64K TTFT 10.7 s (-18.9%), c1 DSpark decode 160.8 tok/s code / 188.8 tok/s 16K+ long-gen, c4 170.5 aggregate. Microbenchmarks bit-exact (0 diff) or within BF16 noise. Topology guide: PP6 = 2.1x slower single-stream; TP2+TP4 asymmetric hurts Marlin tiles.","tier":"community","beta":false,"generation":"ampere","decode_tok_s":160.80000000000001136868377216160297393798828125,"prefill_tok_s":4506.8000000000001818989403545856475830078125,"updated_at":"2026-10-28 15:48:17.404025-06","commit_sha":"ced28259b90a43ec103ecd450b68455a56d2808d","content_hash":"e00265eca8b84734c2c7de2b67d558b0d702d25e","votes":0,"credit":[{"name":"HalfVulpes (Deepinfer-SM80 port + measurements)","url":"https://github.com/HalfVulpes/Deepinfer-SM80"},{"name":"DeepSeek-AI (DeepInfer engine architecture + DeepSeek-V4.1-Flash checkpoint)","url":"https://github.com/deepseek-ai/DeepInfer"},{"name":"vLLM project (V1 engine + TPxPP runtime)","url":"https://github.com/vllm-project/vllm"},{"name":"TileLang + OpenAI Triton (SM80 kernel synthesis)","url":"https://github.com/tile-ai/tilelang"},{"name":"FlashInfer + IST-DASLab Marlin (sparse-MLA + MXFP4/W4A16 Ampere GEMM primitives)","url":"https://github.com/flashinfer-ai/flashinfer"}],"uploaded_by":"localai-recipes","measured":null,"links":{"self":"/api/v1/recipes/deepseek-v4-1-flash-sm80-deepinfer-kernel-port-6x-a100-dspark-k5.json","alternate":"/r/deepseek-v4-1-flash-sm80-deepinfer-kernel-port-6x-a100-dspark-k5"}}]}