Commit Graph

5 Commits

Author SHA1 Message Date
fabolous005 1e3a412563 prain: serve with the string chat template content format 2026-11-04 21:50:46 +01:00
fabolous005 a67238f66b prain: personas for the chats; README on quantization levels and personas
prain web/tui --persona FILE sends the file as the system message ahead of every warm-up and
answer; the page shows its name. Three examples in examples/personas (task, how to answer,
environment, how to use it). A persona costs 2.0-3.2 s once (241-467 tokens), then at most
0.3 s per conversation from the prefix cache.

README rewritten around launching: quick start, the vLLM flags, a quantization table measured
today at equal expert VRAM (bf16 0.90 / int8 2.19 / int4 5.19 tok/s; 2.3k-token prompt 69.5 /
32.3 / 20.5 s; 4 of 6 int8 and 0 of 6 int4 answers identical to bf16, one int4 answer wrong),
how to switch formats, the VRAM budget, writing personas, the chats and the monitor.
2026-10-29 23:55:36 +01:00
fabolous005 0f3911afb5 prain: span profiler with flame graphs (PRAIN_PROFILE: engine step, every model module, MoE route/plan/copy/round, call counts; python -m prain.profile); prain web --host 2026-10-29 08:39:28 +01:00
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
fabolous005 7a78cdee79 prain: command line 2026-10-27 13:52:10 +01:00