Files
llama.cpp/conversion
Aman Gupta d3064fddce convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8) (#32476)
* convert : fix FP8 n-gram table export for qwen4exp

* convert : dequantize block-scaled FP8 weight_scale_inv in ModelOpt checkpoints
2026-11-17 22:25:01 +08:00
..
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-02 18:37:27 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-16 17:32:27 +01:00
2026-11-10 21:54:14 +01:00
2026-10-20 18:33:32 +02:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 11:28:47 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-10-19 23:01:40 +02:00
2026-11-10 21:54:14 +01:00
2026-10-29 15:43:33 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-10-27 11:49:12 +01:00
2026-11-10 21:54:14 +01:00
2026-11-10 21:54:14 +01:00
2026-11-16 20:22:23 +01:00