leavelet 268bcf78da Dump: add 'fh' mode (final_hidden only, fresh prefills allowed) for cache-bust vs cache-hit ...

rid 'dumpfh-' -> dump ONLY the model's final hidden (last token, post-CP-gather = the
first-token source), allowed on FRESH prefills too -> the cache-bust-vs-cache-hit
discriminator (prefill-side vs decode-side). rid 'dump-' keeps the lean per-layer
trajectory (cache-hit only). Flush moved after the CP gather. dump_diff generalized to
compare any two phases.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-17 16:10:41 +00:00

..

sglang

Dump: add 'fh' mode (final_hidden only, fresh prefills allowed) for cache-bust vs cache-hit

2026-06-17 16:10:41 +00:00

pyproject_cpu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject_npu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject_other.toml

chore: extract diffusion_common in python/pyproject_other.toml (#20803)

2026-03-19 10:39:16 +08:00

pyproject_xpu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject.toml

new pyprojectoml

2026-06-10 05:54:43 +08:00