fabolous005 01dce2ffc6 prain: tune searches the auto CPU threshold and writes --cpu-threads; vLLM patch: fit Gemma 4 in 8 GB (tied lm_head without a copy, rope caches sized by max_model_len)

2026-10-27 23:52:53 +01:00

examples

prain: RX 6600 XT example config

2026-10-27 13:52:26 +01:00

patches

prain: tune searches the auto CPU threshold and writes --cpu-threads; vLLM patch: fit Gemma 4 in 8 GB (tied lm_head without a copy, rope caches sized by max_model_len)

2026-10-27 23:52:53 +01:00

prain

prain: tune searches the auto CPU threshold and writes --cpu-threads; vLLM patch: fit Gemma 4 in 8 GB (tied lm_head without a copy, rope caches sized by max_model_len)

2026-10-27 23:52:53 +01:00

scripts

prain: fix vLLM on ROCm (no CUDA capability families), smoke test and benchmark scripts

2026-10-27 16:44:40 +01:00

tests

prain: tune searches the auto CPU threshold and writes --cpu-threads; vLLM patch: fit Gemma 4 in 8 GB (tied lm_head without a copy, rope caches sized by max_model_len)

2026-10-27 23:52:53 +01:00

.gitignore

prain: skeleton

2026-10-27 13:52:04 +01:00

pyproject.toml

prain: skeleton

2026-10-27 13:52:04 +01:00

S

Description

No description provided

370 KiB

Languages

Python 83.8%

HTML 12.2%

Shell 4%