src-e8426e0/docs/reference/tools.md

Command-line tools

The build puts the tools in out/bin (macOS) or build/bin (Windows, Linux).

Run

Tool	Use
nslm-chat	Run one prompt. Read Run and serve
nslm-serve	OpenAI-compatible HTTP server

Measure

Tool	Use
nslm-mova-bench	Prompt and decode speed, memory and machine state
nslm-mova-score	Logits for KLD against a reference
nslm-mova-gen	Greedy and sampled outputs for a set of prompts
nslm-mova-plcheck	Prompt-lookup decode against plain decode. The two must be identical
nslm-mova-kbench	Speed of one kernel at the MoVA shapes. There is one program for each GPU API. The Metal program also selects Metal kernel variants
nslm-mova-refcheck	The GPU engine against a C reference forward on the CPU (KL, argmax, router choices)
nslm-mova-routes	Router choices for a prompt and a generation, for expert-cache studies
nslm-qwen4-gen	Greedy generation of one prompt through the Qwen3.8-Flash-Next CUDA engine, with prompt and decode speed
nslm-qwen4-kld	KL divergence, top-1 agreement and perplexity of a Qwen3.8-Flash-Next model against a reference, on one text

Make models

Tool	Use
nslm-moe	Seed search for experts (--scope gud) and MLA projections (--scope mla). Qwen3.8-Flash-Next experts take --imatrix
nslm-mova-mlacapture	Activation statistics and X^T X of the MLA projection inputs
nslm-mova-pack	Write a model folder
nslm-qwen4-pack	Write a Qwen3.8-Flash-Next MLX folder with seed experts, from an MLX base folder
nslm-qwen4-emulate	Write seed experts into Unsloth's Q8_0 GGUF shards in place, so that llama.cpp runs them. A map takes each expert from one of several packs

Read Make a model folder.

Python tools (tools/)

Tool	Use
nanoseedlm_k2.py	The MLX loader for K2-Horizon
nanoseedlm_qwen4.py	The MLX loader for Qwen3.8-Flash-Next (mlx-vlm)
nanoseedlm_seeds.py	The seed kernels and modules that the MLX loaders share
qwen4_golden.py	A tiny random Qwen3.8-Flash-Next model and its mlx-vlm logits, for tests/test_qwen4_ref.c
qwen4_cache_sim.py	Replays a routing trace (Q4E_ROUTES) through expert cache policies: LRU, LFU, a hot set and the optimum
hf_cuda_test.sh	Build and run CUDA tests on an HF Jobs GPU node
hf_qwen4_gen.sh	Run a Qwen3.8-Flash-Next pack through nslm-qwen4-gen on an HF Jobs GPU node
hf_qwen4_kld.sh	Score packs with nslm-qwen4-kld against a reference model on wikitext-2, on an HF Jobs GPU node
hf_llama_kld.sh	Score Unsloth packs and emulated seed packs against BF16 in llama.cpp, with the BF16 PLE table
hf_qwen4_routes.sh	Record routing traces of a pack on chat and code text, on an HF Jobs GPU node
qwen4_tier_map.py	Write a per-expert tier map from routing traces (most used experts), at random, or by projection
mova_capture.py	Activation statistics for the expert search, through MLX
mova_score.py	Scores in MLX
mova_export.py	Inputs for nslm-mova-score, nslm-mova-gen, nslm-mova-bench and route studies
tokenizer_golden.py, template_golden.py, mova_affine_golden.py	Golden files for the tests
serve_bench.py	Server speed. It waits for an idle GPU and records machine state