From 9438af5a8caf6cc5508ae08aaf8f35aaa74d5c3d Mon Sep 17 00:00:00 2001 From: biondizzle Date: Sat, 9 May 2026 06:47:26 +0000 Subject: [PATCH] Add commit hashes to run history table --- README.md | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 0e18c2d..bb748bd 100644 --- a/README.md +++ b/README.md @@ -59,11 +59,14 @@ python3 /root/nvidia-meeting/deepseek-v4-quant/scripts/quantize_nvfp4.py --valid ## Run History (forward progression) -| Run | Date | Script | Calib | Result | Root Cause | Fix | +| Run | Date | Commit | Calib | Result | Root Cause | Fix | |-----|------|--------|-------|--------|------------|-----| -| 1 | May 7 | shell wrapper, FP8 source | 256 | ❌ Crashed at batch probing | `o_b_proj` shape mismatch — finegrained_fp8 wraps MLA projections incorrectly with FP8 source | Use BF16 source (dequantized) | -| 2 | May 8-9 | shell wrapper, BF16 source | 128 | ❌ Crashed at export (128/128 calib ✅) | `get_activation_scaling_factor` reads stale GPU amax → CUDA illegal memory access | Snapshot amax to CPU immediately after calibration | -| 3 | May 9 | `quantize_nvfp4.py` v1 | 128 | 🔄 Running | — | — | +| 1 | May 7 | shell wrapper (pre-repo) | 256 | ❌ Crashed at batch probing | `o_b_proj` shape mismatch — finegrained_fp8 wraps MLA projections incorrectly with FP8 source | Use BF16 source (dequantized) | +| 2 | May 8-9 | shell wrapper (pre-repo) | 128 | ❌ Crashed at export (128/128 calib ✅) | `get_activation_scaling_factor` reads stale GPU amax → CUDA illegal memory access | Snapshot amax to CPU immediately after calibration | +| 3 | May 9 | `3907838` | 128 | 🔄 Running | — | — | + +**If Run 3 succeeds**, the v2 script (`6eeba26`) is reference only — no need to adopt it. +**If Run 3 fails at export**, use commit `6eaba26` (adds amax snapshot + force CPU + validate mode). **Key lesson from Run 2:** The `use_seq_device_map` mode shuffles layers through GPU for calibration. Quantizer amax tensors sit in VRAM for 5+ hours while CUDA's allocator churns memory. By export time, the GPU tensor metadata is valid but the underlying memory has been recycled — reading it triggers `cudaErrorIllegalAddress`. The fix is to copy amax to CPU *immediately* after calibration, before any further GPU operations.