ltx23_quantize_fp8

Packages

chatterbox
- chatterbox Reference
cornfab
- cornfab Reference
diffuseR
earshot
- run_app
fyi
- fyi Reference
llamaR
- llamaR Reference
rapt
- rapt Reference
rformat
- rformat Reference
saber
- saber Reference
stt.api
tinypkgr
- tinypkgr Reference
tinyrox
- tinyrox Reference
tts.api
- tts.api Reference
whisper

Quantize an LTX-2.3 checkpoint to FP8 shards

Description

Streams the single-file bf16 checkpoint tensor by tensor. DiT attention/FFN linear weights are stored as float8_e4m3fn with a float32 absmax/448 per-tensor scale (<key>_scale sibling); everything else is copied through unchanged. Output shards carry the original key names plus a manifest for skip-if-exists.

Usage

ltx23_quantize_fp8(checkpoint_path,
                   output_dir = file.path(tools::R_user_dir("diffuseR", "data"), "ltx2.3-fp8"),
                   shard_bytes = 4e+09, force = FALSE, verbose = TRUE)

Arguments

checkpoint_path: Source .safetensors (46 GB bf16 single file).
output_dir: Output directory for shards + manifest.
shard_bytes: Numeric. Approximate shard size (default 4 GB).
force: Logical. Re-quantize even if a valid manifest exists.
verbose: Logical.

Value

Invisibly, the manifest list.