lna-lab inc.

Popular repositories Loading

1. distill-kura distill-kura Public

   蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.

   Python 49 7

2. blackwell-geforce-nvfp4-gemm blackwell-geforce-nvfp4-gemm Public

   NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.

   Python 25 2

3. flash-next-8gb flash-next-8gb Public

   Run a 177B model (Qwen3.8-Flash-Next) on an 8 GB laptop GPU. Measured: 6.6 GiB VRAM, 47.8 GiB RAM, 34-35 tok/s. The n-gram table stays on disk; the experts run on CPU.

   Python 20 5

4. lna-es lna-es Public

   あらゆるジャンルのテキストをLLMを使いNeo4Jグラフ化して、グラフのみのデータから意味的復元をするシステムのスターター（MCP対応予定）

   16 1

5. gemma4-12b-vllm-sm120 gemma4-12b-vllm-sm120 Public

   Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode.

   Python 14

6. GGUF-to-NVFP4-SM120 GGUF-to-NVFP4-SM120 Public

   Lna-Lab production pipeline: GGUF -> modelopt-format NVFP4 + working MTP head for vLLM on RTX PRO 6000 Blackwell (SM120). Stages 2 (NVFP4) and 3 (MTP graft) are Lna-Lab originals; stage 1 (GGUF->bf…

   Python 10 3