{
  "schema_version": "1.0",
  "url": "https://cerinamroth.com/ml/solutions/",
  "title": "MoE Training & Inference Guides — Cerin Amroth",
  "description": "One page per ordinary problem in quantized Mixture-of-Experts training and serving, each routed to the canonical package with install, verification, limitations and evidence.",
  "date_modified": "2026-10-24",
  "representations": {
    "json": "https://cerinamroth.com/data/pages/ml/solutions.json",
    "markdown": "https://cerinamroth.com/data/pages/ml/solutions.md"
  },
  "headings": [
    {
      "level": 1,
      "id": null,
      "text": "Solutions — one page per problem"
    },
    {
      "level": 2,
      "id": "experts4bit-qlora",
      "text": "experts4bit-qlora — docs/SOLUTIONS.md at 605d21e67958"
    },
    {
      "level": 2,
      "id": "grouped-nf4-gemm",
      "text": "grouped-nf4-gemm — docs/SOLUTIONS.md at 30adb1bfa76f"
    }
  ],
  "links": [
    {
      "text": "Home",
      "url": "https://cerinamroth.com/"
    },
    {
      "text": "ML systems",
      "url": "https://cerinamroth.com/ml/"
    },
    {
      "text": "docs/SOLUTIONS.md",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/SOLUTIONS.md"
    },
    {
      "text": "605d21e67958",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/commit/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d"
    },
    {
      "text": "Why does `load_in_4bit` still OOM on a Mixture-of-Experts model?",
      "url": "https://cerinamroth.com/ml/solutions/bitsandbytes-moe-load-in-4bit-still-ooms/"
    },
    {
      "text": "experts4bit-qlora",
      "url": "https://cerinamroth.com/ml/experts4bit-qlora/"
    },
    {
      "text": "How do I train and serve MoE models released in MXFP4 (gpt-oss, DeepSeek-V4)?",
      "url": "https://cerinamroth.com/ml/solutions/mxfp4-moe-training-and-residency/"
    },
    {
      "text": "experts4bit-qlora",
      "url": "https://cerinamroth.com/ml/experts4bit-qlora/"
    },
    {
      "text": "How do I offload MoE experts to host RAM, or serve and train them from an NVMe arena?",
      "url": "https://cerinamroth.com/ml/solutions/offload-moe-experts-to-cpu-or-nvme/"
    },
    {
      "text": "experts4bit-qlora",
      "url": "https://cerinamroth.com/ml/experts4bit-qlora/"
    },
    {
      "text": "How do I QLoRA-train the fused experts of a MoE (per-expert LoRA on 4-bit experts)?",
      "url": "https://cerinamroth.com/ml/solutions/qlora-fused-moe-experts/"
    },
    {
      "text": "experts4bit-qlora",
      "url": "https://cerinamroth.com/ml/experts4bit-qlora/"
    },
    {
      "text": "How can I run a Mixture-of-Experts model larger than my GPU's VRAM?",
      "url": "https://cerinamroth.com/ml/solutions/run-moe-larger-than-vram/"
    },
    {
      "text": "experts4bit-qlora",
      "url": "https://cerinamroth.com/ml/experts4bit-qlora/"
    },
    {
      "text": "How do I serve a large MoE on a consumer GPU (RTX 5090 class)?",
      "url": "https://cerinamroth.com/ml/solutions/serve-large-moe-on-a-consumer-gpu/"
    },
    {
      "text": "experts4bit-qlora",
      "url": "https://cerinamroth.com/ml/experts4bit-qlora/"
    },
    {
      "text": "docs/SOLUTIONS.md",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/SOLUTIONS.md"
    },
    {
      "text": "30adb1bfa76f",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/commit/30adb1bfa76f95f9ce4a4c29734b8f36de907eca"
    },
    {
      "text": "How do I run paged decode attention over an FP8 KV cache for a quantized MoE serving path, with sliding windows, attention sinks and a custom scale?",
      "url": "https://cerinamroth.com/ml/solutions/fp8-paged-attention-for-moe-serving/"
    },
    {
      "text": "grouped-nf4-gemm",
      "url": "https://cerinamroth.com/ml/grouped-nf4-gemm/"
    },
    {
      "text": "How do I run a single-token INT4 decode GEMV over routed MoE experts, and pack calibrated (GPTQ) weights for it?",
      "url": "https://cerinamroth.com/ml/solutions/int4-decode-gemv/"
    },
    {
      "text": "grouped-nf4-gemm",
      "url": "https://cerinamroth.com/ml/grouped-nf4-gemm/"
    },
    {
      "text": "How do I run MoE expert inference natively on MXFP4 (e2m1 + e8m0) weights, straight from the released checkpoint bytes?",
      "url": "https://cerinamroth.com/ml/solutions/native-mxfp4-moe-inference/"
    },
    {
      "text": "grouped-nf4-gemm",
      "url": "https://cerinamroth.com/ml/grouped-nf4-gemm/"
    },
    {
      "text": "How do I run a grouped GEMM directly on NF4 packed MoE expert weights, without dequantizing to bf16 first?",
      "url": "https://cerinamroth.com/ml/solutions/nf4-grouped-gemm-without-bf16-materialization/"
    },
    {
      "text": "grouped-nf4-gemm",
      "url": "https://cerinamroth.com/ml/grouped-nf4-gemm/"
    },
    {
      "text": "How do I run a MoE whose experts do not fit in VRAM, streaming them from pinned host RAM or an NVMe arena?",
      "url": "https://cerinamroth.com/ml/solutions/stream-moe-experts-from-host-or-nvme/"
    },
    {
      "text": "grouped-nf4-gemm",
      "url": "https://cerinamroth.com/ml/grouped-nf4-gemm/"
    },
    {
      "text": "How do I verify that the quantized expert bytes I serve or train on are the released checkpoint bytes?",
      "url": "https://cerinamroth.com/ml/solutions/verify-quantized-checkpoint-provenance/"
    },
    {
      "text": "grouped-nf4-gemm",
      "url": "https://cerinamroth.com/ml/grouped-nf4-gemm/"
    },
    {
      "text": "pjordanandrsn/experts4bit-qlora@605d21e67958",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/commit/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d"
    },
    {
      "text": "pjordanandrsn/grouped-nf4-gemm@30adb1bfa76f",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/commit/30adb1bfa76f95f9ce4a4c29734b8f36de907eca"
    },
    {
      "text": "pjordanandrsn/experts4bit-qlora@605d21e67958",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/commit/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d"
    },
    {
      "text": "docs/SOLUTIONS.md",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/SOLUTIONS.md"
    },
    {
      "text": "docs/solutions/bitsandbytes-moe-load-in-4bit-still-ooms.md",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/bitsandbytes-moe-load-in-4bit-still-ooms.md"
    },
    {
      "text": "docs/solutions/mxfp4-moe-training-and-residency.md",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/mxfp4-moe-training-and-residency.md"
    },
    {
      "text": "docs/solutions/offload-moe-experts-to-cpu-or-nvme.md",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/offload-moe-experts-to-cpu-or-nvme.md"
    },
    {
      "text": "docs/solutions/qlora-fused-moe-experts.md",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/qlora-fused-moe-experts.md"
    },
    {
      "text": "docs/solutions/run-moe-larger-than-vram.md",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/run-moe-larger-than-vram.md"
    },
    {
      "text": "docs/solutions/serve-large-moe-on-a-consumer-gpu.md",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/serve-large-moe-on-a-consumer-gpu.md"
    },
    {
      "text": "files at this commit",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora/tree/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d"
    },
    {
      "text": "latest on main",
      "url": "https://github.com/pjordanandrsn/experts4bit-qlora"
    },
    {
      "text": "pjordanandrsn/grouped-nf4-gemm@30adb1bfa76f",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/commit/30adb1bfa76f95f9ce4a4c29734b8f36de907eca"
    },
    {
      "text": "docs/SOLUTIONS.md",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/SOLUTIONS.md"
    },
    {
      "text": "docs/solutions/fp8-paged-attention-for-moe-serving.md",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/fp8-paged-attention-for-moe-serving.md"
    },
    {
      "text": "docs/solutions/int4-decode-gemv.md",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/int4-decode-gemv.md"
    },
    {
      "text": "docs/solutions/native-mxfp4-moe-inference.md",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/native-mxfp4-moe-inference.md"
    },
    {
      "text": "docs/solutions/nf4-grouped-gemm-without-bf16-materialization.md",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/nf4-grouped-gemm-without-bf16-materialization.md"
    },
    {
      "text": "docs/solutions/stream-moe-experts-from-host-or-nvme.md",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/stream-moe-experts-from-host-or-nvme.md"
    },
    {
      "text": "docs/solutions/verify-quantized-checkpoint-provenance.md",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/verify-quantized-checkpoint-provenance.md"
    },
    {
      "text": "files at this commit",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm/tree/30adb1bfa76f95f9ce4a4c29734b8f36de907eca"
    },
    {
      "text": "latest on main",
      "url": "https://github.com/pjordanandrsn/grouped-nf4-gemm"
    }
  ],
  "structured_data": [
    {
      "@context": "https://schema.org",
      "@type": "WebPage",
      "name": "MoE Training & Inference Guides — Cerin Amroth",
      "url": "https://cerinamroth.com/ml/solutions/",
      "inLanguage": "en",
      "description": "One page per ordinary problem in quantized Mixture-of-Experts training and serving, each routed to the canonical package with install, verification, limitations and evidence.",
      "mainEntityOfPage": "https://cerinamroth.com/ml/solutions/"
    },
    {
      "@context": "https://schema.org",
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://cerinamroth.com/"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "ML systems",
          "item": "https://cerinamroth.com/ml/"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Solutions"
        }
      ]
    }
  ],
  "content_markdown": "[Home](https://cerinamroth.com/) › [ML systems](https://cerinamroth.com/ml/) › Solutions \n\n# Solutions — one page per problem\n\nChoose the problem you are trying to solve. Each guide gives an install route, a working example, the result to expect, and the limits of the approach, with links to its evidence.\n\n \n\n## `experts4bit-qlora` — [docs/SOLUTIONS.md](https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/SOLUTIONS.md) at [605d21e67958](https://github.com/pjordanandrsn/experts4bit-qlora/commit/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d)\n\n | Problem | Package\n | [Why does `load_in_4bit` still OOM on a Mixture-of-Experts model?](https://cerinamroth.com/ml/solutions/bitsandbytes-moe-load-in-4bit-still-ooms/)\nbitsandbytes' 4-bit walker replaces only nn.Linear and skips a fused MoE's 3-D expert stacks, so load_moe_4bit_streaming quantises exactly those stacks and verify_moe_4bit proves it. | [`experts4bit-qlora`](https://cerinamroth.com/ml/experts4bit-qlora/)\n | [How do I train and serve MoE models released in MXFP4 (gpt-oss, DeepSeek-V4)?](https://cerinamroth.com/ml/solutions/mxfp4-moe-training-and-residency/)\nChoose an MXFP4 loading or native-byte execution route by model and task; gpt-oss arena training is refused, while its separate experimental expert-training path remains unlicensed. | [`experts4bit-qlora`](https://cerinamroth.com/ml/experts4bit-qlora/)\n | [How do I offload MoE experts to host RAM, or serve and train them from an NVMe arena?](https://cerinamroth.com/ml/solutions/offload-moe-experts-to-cpu-or-nvme/)\nBind pinned host RAM or a baked NVMe arena to a real model with the streaming loader and the nvme_residency, mxfp4_nvme_residency and nvme_train_residency engines. | [`experts4bit-qlora`](https://cerinamroth.com/ml/experts4bit-qlora/)\n | [How do I QLoRA-train the fused experts of a MoE (per-expert LoRA on 4-bit experts)?](https://cerinamroth.com/ml/solutions/qlora-fused-moe-experts/)\nExpertsLoRA adds a trainable per-expert low-rank delta before each routed expert's activation over a frozen NF4 stack PEFT cannot target; enable_fast_train runs it on grouped kernels. | [`experts4bit-qlora`](https://cerinamroth.com/ml/experts4bit-qlora/)\n | [How can I run a Mixture-of-Experts model larger than my GPU's VRAM?](https://cerinamroth.com/ml/solutions/run-moe-larger-than-vram/)\nChoose a residency path by workload and by the memory tier that ran out: pinned-host expert streaming, dense offload, profiled hot residency, or an NVMe arena. | [`experts4bit-qlora`](https://cerinamroth.com/ml/experts4bit-qlora/)\n | [How do I serve a large MoE on a consumer GPU (RTX 5090 class)?](https://cerinamroth.com/ml/solutions/serve-large-moe-on-a-consumer-gpu/)\nThe paged decode runner with experts on grouped-nf4-gemm's kernels is the measured serving path on one RTX 5090-class GPU; the HTTP shim is a separate reference-path deployment. | [`experts4bit-qlora`](https://cerinamroth.com/ml/experts4bit-qlora/)\n\n## `grouped-nf4-gemm` — [docs/SOLUTIONS.md](https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/SOLUTIONS.md) at [30adb1bfa76f](https://github.com/pjordanandrsn/grouped-nf4-gemm/commit/30adb1bfa76f95f9ce4a4c29734b8f36de907eca)\n\n | Problem | Package\n | [How do I run paged decode attention over an FP8 KV cache for a quantized MoE serving path, with sliding windows, attention sinks and a custom scale?](https://cerinamroth.com/ml/solutions/fp8-paged-attention-for-moe-serving/)\nfp8_paged_decode_attention runs paged flash-decode over an E4M3 KV cache with windows, sinks and a custom scale; the fp8 compute path is supported on sm_89+, the f32 path (the sm_80–sm_88 default) since #319's close. | [`grouped-nf4-gemm`](https://cerinamroth.com/ml/grouped-nf4-gemm/)\n | [How do I run a single-token INT4 decode GEMV over routed MoE experts, and pack calibrated (GPTQ) weights for it?](https://cerinamroth.com/ml/solutions/int4-decode-gemv/)\ngemv_int4_b32 runs the batch-1 int4-b32 decode GEMV with exact integer accumulation, and gptq_pack_int4_b32 packs calibrated weights onto the same bytes; the served GEMV's throughput and the calibrated pack's quality are measured-private, while the small-M GEMM and the two opt-in GEMV variants are measured in public, and the split-K planner plans from (N, K) alone since K30 read its row-count term OFF. | [`grouped-nf4-gemm`](https://cerinamroth.com/ml/grouped-nf4-gemm/)\n | [How do I run MoE expert inference natively on MXFP4 (e2m1 + e8m0) weights, straight from the released checkpoint bytes?](https://cerinamroth.com/ml/solutions/native-mxfp4-moe-inference/)\ngemm_mxfp4_grouped multiplies gpt-oss and Kimi-class experts on their released e2m1 blocks and e8m0 scales, with no requantization to NF4 and no bf16 materialization. | [`grouped-nf4-gemm`](https://cerinamroth.com/ml/grouped-nf4-gemm/)\n | [How do I run a grouped GEMM directly on NF4 packed MoE expert weights, without dequantizing to bf16 first?](https://cerinamroth.com/ml/solutions/nf4-grouped-gemm-without-bf16-materialization/)\ngemm_4bit_grouped runs the routed MoE expert GEMM on bitsandbytes NF4 packed weights in one Triton launch, decoding nibbles in registers with fp32 accumulation and no bf16 expert tensor. | [`grouped-nf4-gemm`](https://cerinamroth.com/ml/grouped-nf4-gemm/)\n | [How do I run a MoE whose experts do not fit in VRAM, streaming them from pinned host RAM or an NVMe arena?](https://cerinamroth.com/ml/solutions/stream-moe-experts-from-host-or-nvme/)\nThe kernel-side storage primitives for experts that do not fit VRAM: the NVMe arena bake and O_DIRECT reader, the pinned-DRAM row tier and low-level residency, and the GPU-driven host gather. | [`grouped-nf4-gemm`](https://cerinamroth.com/ml/grouped-nf4-gemm/)\n | [How do I verify that the quantized expert bytes I serve or train on are the released checkpoint bytes?](https://cerinamroth.com/ml/solutions/verify-quantized-checkpoint-provenance/)\nfile_tensor_sha256, provenance_table and verify_arena_matches hash safetensors byte ranges against the loaded and baked bytes, and verify_provenance re-derives a run's hash table. | [`grouped-nf4-gemm`](https://cerinamroth.com/ml/grouped-nf4-gemm/)\n\n \n\nrendered from experts4bit-qlora 0.58.1 · source: [pjordanandrsn/experts4bit-qlora@605d21e67958](https://github.com/pjordanandrsn/experts4bit-qlora/commit/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d) · checked 2026-10-25\n\nrendered from grouped-nf4-gemm 0.51.0 · source: [pjordanandrsn/grouped-nf4-gemm@30adb1bfa76f](https://github.com/pjordanandrsn/grouped-nf4-gemm/commit/30adb1bfa76f95f9ce4a4c29734b8f36de907eca) · checked 2026-10-25\n\n \n\nSources and publication details\n\nThe generated ML documentation surfaces on this site (`/ml/` and its sub-pages, `/ml/packages.json`, both `llms.txt` files) are derived from the repositories below at pinned commits; each repository's `docs/claims.json` at that commit is the only source for numbers. Pages with their own source are listed separately.\n\n- [pjordanandrsn/experts4bit-qlora@605d21e67958](https://github.com/pjordanandrsn/experts4bit-qlora/commit/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d) (2026-10-24) · package `experts4bit-qlora` 0.58.1 · PyPI 0.58.1 (published) · documents: [`docs/SOLUTIONS.md`](https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/SOLUTIONS.md), [`docs/solutions/bitsandbytes-moe-load-in-4bit-still-ooms.md`](https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/bitsandbytes-moe-load-in-4bit-still-ooms.md), [`docs/solutions/mxfp4-moe-training-and-residency.md`](https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/mxfp4-moe-training-and-residency.md), [`docs/solutions/offload-moe-experts-to-cpu-or-nvme.md`](https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/offload-moe-experts-to-cpu-or-nvme.md), [`docs/solutions/qlora-fused-moe-experts.md`](https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/qlora-fused-moe-experts.md), [`docs/solutions/run-moe-larger-than-vram.md`](https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/run-moe-larger-than-vram.md), [`docs/solutions/serve-large-moe-on-a-consumer-gpu.md`](https://github.com/pjordanandrsn/experts4bit-qlora/blob/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d/docs/solutions/serve-large-moe-on-a-consumer-gpu.md) · registers: none · synced 2026-10-25T00:58:32Z · [files at this commit](https://github.com/pjordanandrsn/experts4bit-qlora/tree/605d21e67958fa94d5e73fc3a95ffcb5c8eae02d) · [latest on main](https://github.com/pjordanandrsn/experts4bit-qlora) (unpinned; not the source of any fact rendered here)\n- [pjordanandrsn/grouped-nf4-gemm@30adb1bfa76f](https://github.com/pjordanandrsn/grouped-nf4-gemm/commit/30adb1bfa76f95f9ce4a4c29734b8f36de907eca) (2026-10-24) · package `grouped-nf4-gemm` 0.51.0 · PyPI 0.51.0 (published) · documents: [`docs/SOLUTIONS.md`](https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/SOLUTIONS.md), [`docs/solutions/fp8-paged-attention-for-moe-serving.md`](https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/fp8-paged-attention-for-moe-serving.md), [`docs/solutions/int4-decode-gemv.md`](https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/int4-decode-gemv.md), [`docs/solutions/native-mxfp4-moe-inference.md`](https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/native-mxfp4-moe-inference.md), [`docs/solutions/nf4-grouped-gemm-without-bf16-materialization.md`](https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/nf4-grouped-gemm-without-bf16-materialization.md), [`docs/solutions/stream-moe-experts-from-host-or-nvme.md`](https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/stream-moe-experts-from-host-or-nvme.md), [`docs/solutions/verify-quantized-checkpoint-provenance.md`](https://github.com/pjordanandrsn/grouped-nf4-gemm/blob/30adb1bfa76f95f9ce4a4c29734b8f36de907eca/docs/solutions/verify-quantized-checkpoint-provenance.md) · registers: none · synced 2026-10-24T14:51:49Z · [files at this commit](https://github.com/pjordanandrsn/grouped-nf4-gemm/tree/30adb1bfa76f95f9ce4a4c29734b8f36de907eca) · [latest on main](https://github.com/pjordanandrsn/grouped-nf4-gemm) (unpinned; not the source of any fact rendered here)\n",
  "content_sha256": "df2cfe6421c33214710bf205af6a74da3db625193adefacc4484159a488fbd67"
}