Point obliteratus at an FP8 or NVFP4 checkpoint and it just works:
the loader detects the format from config.json + safetensors metadata
(no weight loads), dequantizes shard-by-shard to a temporary BF16 copy,
then runs the normal float pipeline and saves BF16.
Supported layouts:
- FP8 DeepSeek-style block-wise (weight_scale_inv + weight_block_size)
- FP8 per-channel / per-tensor (compressed-tensors, ModelOpt)
- NVFP4 ModelOpt (uint8 nibbles + FP8 group scales + FP32 global),
including MIXED_PRECISION checkpoints (FP8 mixer + NVFP4 experts)
- NVFP4 compressed-tensors (reciprocal scales)
Design:
- New pure-torch obliteratus/models/quant_dequant.py; no new deps.
NVFP4 unpack uses torch.float4_e2m1fn_x2 when a runtime probe proves
it works, else a chunked nibble LUT (bounds transient int64 index
memory; a naive implementation OOMed at 96GB on a 30B model).
- Scale keys are dropped only when their base weight exists in the
same shard, so legitimate params ending in _scale (logit_scale et al.)
survive.
- Unsupported schemes (fbgemm, quanto, W4A4, ...) fail loudly at load,
naming the scheme.
- Surgery guards: float8 or packed uint8 reaching _dequantize_weight or
any fused-MoE path raises RuntimeError instead of silently upcasting
(bitsandbytes quant_state params are explicitly excluded).
- Save path strips quantization metadata and logs that output is BF16;
re-quantization for serving is out of scope (llm-compressor/modelopt).
- CLI: new --trust-remote-code flag; help text documents auto-detection.
Validated end-to-end on 1x A100-80GB (see PR description):
Nemotron-3-Nano-Omni-30B NVFP4 (mixed) and FP8, Qwen3-8B-FP8
(block-wise) vs Qwen3-8B BF16 baseline (perplexity 4.23 vs 4.33).
Salvage the still-relevant functional work from PR #48: add non-UTF-8 console fallbacks, use platform temporary directories, make pipeline log output encoding-safe, and defer heavyweight analysis imports. The obsolete contributed CI workflow and already-corrected remote URL are intentionally excluded.
Add a --gpu-memory-utilization flag (0.0-1.0, default 0.85) that controls
the fraction of GPU VRAM available for model loading. Plumbed from CLI
through AbliterationPipeline to load_model's max_memory calculation.
Useful on dedicated GPU setups where the default 15% reserve is wasteful
and causes unnecessary CPU offloading on models that would otherwise fit.
The README/CONTRIBUTING examples used `obliteratus aggregate --format ...` but the CLI only accepted `--dir`.
This adds `--format {summary,latex}`, `--metric`, and `--min-runs` to the aggregate command, reuses community LaTeX table generation, and adds CLI parsing tests to align behavior with documented usage.
New `obliteratus gpu-calc` subcommand estimates minimum GPU count from
model params, dtype, and GPU VRAM. Auto-detects param counts from HF
configs including MoE expert structure.
README now covers --dtype, --quantization flags, the gpu-calc command,
and references both in the "Choosing the right setup" table.
When --data-parallel is passed and the model fits on a single GPU,
wraps it with nn.DataParallel to split prompt batches across all
available GPUs during activation collection. Batch size scales by
GPU count. Hooks already move activations to CPU so they work
correctly across replicas.
Adds --gpus flag to obliterate, run, and tourney commands for controlling
which GPUs to use (sets CUDA_VISIBLE_DEVICES). Works both locally and with
--remote. Models are automatically split across selected GPUs via
accelerate's device_map="auto". Also adds gpus field to remote YAML config.
Adds --remote [user@]host flag to obliterate, run, and tourney commands,
enabling execution on remote GPU nodes via SSH. Also supports a remote:
section in YAML configs. The remote runner handles SSH connectivity checks,
GPU detection, auto-installation of obliteratus, log streaming, and result
syncing back to the local machine via scp.
Brian Bell