vh 911ff20356 feat(erp-seat): NVFP4A16 quant pipeline for the Gemma-4 26B-A4B MoE ERP tune + ana-ml2 GPU1 serve stack ...

- services/erp-seat-quant/quant_nvfp4a16_gemma4_moe.py: linearize_moe first (playbook §3.15),
  asserts the expert Linear count, routers/vision/audio/norms/lm_head ignored, W4A16 for RP
  long-session fidelity, post-steps restore processor configs + template and reset the
  tokenizer truncation cap (§3.14); --dry-run proves targets before GPU time
- services/erp-seat-quant/run_quant_erp_v6.sh: detached container on GPU1 (vllm-llmcompressor)
- stacks/erp-seat: serve recipe copied from gemma4-charrp, true served name only, port 8021

2026-09-08 21:55:28 -07:00

..

quant_nvfp4a16_gemma4_moe.py

feat(erp-seat): NVFP4A16 quant pipeline for the Gemma-4 26B-A4B MoE ERP tune + ana-ml2 GPU1 serve stack

2026-09-08 21:55:28 -07:00

run_quant_erp_v6.sh

feat(erp-seat): NVFP4A16 quant pipeline for the Gemma-4 26B-A4B MoE ERP tune + ana-ml2 GPU1 serve stack

2026-09-08 21:55:28 -07:00