Popular repositories Loading
-
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.
-
flash-next-8gb
flash-next-8gb PublicRun 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.
-
blackwell-geforce-nvfp4-gemm
blackwell-geforce-nvfp4-gemm PublicNVFP4 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.
-
gemma4-12b-vllm-sm120
gemma4-12b-vllm-sm120 PublicReproducible 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
-
Repositories
- 1017Projects Public
- 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.
- DSH-CODEX-subscription Public
- DeepSeek-V4.1-Flash-EXL3-DGX-Spark-recipe Public Forked from vcruz305/DeepSeek-V4.1-Flash-EXL3-DGX-Spark-recipe
- vllm-exl3 Public Forked from vcruz305/vllm-exl3
Serve EXL3 (ExLlamaV3 trellis) quantized models on vLLM fork runtimes — any architecture, mixed per-layer bitrates, composable with source-format non-routed weights
- dsv4-carve Public
DeepSeek-V4-Flash-Vision 305B EXL3 on 8x16GB: 380K context, 4 streams, DSpark3 — Lna-Lab serving recipe
- 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.
- Ashigaru-Search Public
- DS4-combination Public
- LNAIME Public