This website requires JavaScript.
Explore
Help
Register
Sign In
fabolous005
/
prain
Watch
1
Star
0
Fork
0
You've already forked prain
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
Files
216cd76a77be13c978e3012a3ce8a8641bf6d245
prain
/
scripts
T
History
fabolous005
708e152549
prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant
2026-10-28 22:07:25 +01:00
..
bench.py
prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant
2026-10-28 22:07:25 +01:00
build.sh
prain: fix vLLM on ROCm (no CUDA capability families), smoke test and benchmark scripts
2026-10-27 16:44:40 +01:00
draft_effect.py
prain: warm-up and draft measurement scripts
2026-10-27 15:56:48 +01:00
env.sh
prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant
2026-10-28 22:07:25 +01:00
greedy.py
prain: skeleton
2026-10-27 13:52:04 +01:00
measure.py
prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant
2026-10-28 22:07:25 +01:00
quality.py
prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant
2026-10-28 22:07:25 +01:00
smoke.sh
prain: fix vLLM on ROCm (no CUDA capability families), smoke test and benchmark scripts
2026-10-27 16:44:40 +01:00
tune_moe.py
prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant
2026-10-28 22:07:25 +01:00
warm_effect.py
prain: warm-up and draft measurement scripts
2026-10-27 15:56:48 +01:00