From 24e3b3745dfcdbcf6b5804bce10a42293a6c2bc6 Mon Sep 17 00:00:00 2001 From: biondizzle Date: Fri, 8 May 2026 17:23:10 +0000 Subject: [PATCH] Pin modelopt and transformers versions in README --- README.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/README.md b/README.md index 98a3451..6c4ce24 100644 --- a/README.md +++ b/README.md @@ -57,6 +57,15 @@ Runs NVIDIA's official ModelOpt PTQ pipeline (`hf_ptq.py`) with full `nvfp4` qua **Runtime:** Model loading takes ~53 minutes. Quantization + calibration takes several hours. Total expect 6-12 hours. +## Dependencies (pinned versions) + +- **nvidia-modelopt:** `0.45.0.dev64+g579fc6c31` (installed from git, not PyPI) +- **transformers:** `5.8.0.dev0` (from git, required for DeepSeekV4 support) +- **kernels:** latest (`pip install -U kernels` — needed for finegrained FP8 ops) +- **Python:** 3.10 + +The `quant_module_patched.py` fix is for **modelopt 0.45.0.dev64** specifically. Later versions may include the fix natively — check before applying. Using a different modelopt version may cause patches to fail or V4 quantization to break. + ## Key Notes - Use BF16 source — V4's mixed precision causes issues, FP8 source has kernel problems on Blackwell