Gahow Wang

gahow created branch main in gahow/ali-trace-tools

2026-04-21 15:45:51 +00:00

gahow created repository gahow/ali-trace-tools

2026-04-21 15:45:32 +00:00

gahow pushed to main at gahow/quant

2026-04-18 08:11:02 +00:00

cdaca4bc2a Merge branch 'feat/us-alpha-phase1'

f5e8c708f3 feat: add PIT OHLCV runner and fetch support

c015873ee1 feat: add strict US alpha research pipeline

bf6fccfd11 feat: add regime and breakout alpha modules

7853eafe55 feat: add PIT-aware tradable universe mask

Compare 9 commits »

gahow pushed to main at gahow/aituner

2026-04-18 08:10:29 +00:00

dfe792ff6f docs: add q235b prefill 0-32k tight summary

gahow pushed to main at gahow/aituner

2026-04-17 12:45:24 +00:00

d237fc2723 docs: expand qwen27b 0-8k compare summary

gahow pushed to main at gahow/aituner

2026-04-17 11:25:33 +00:00

9919b9a7bd configs: add q235b prefill 1s 2s 0-32k study

gahow pushed to main at gahow/aituner

2026-04-17 11:20:46 +00:00

34eb495b3e configs: add qwen235b prefill 0-32k study

gahow pushed to main at gahow/kvcache-simulator

2026-04-17 11:15:25 +00:00

1906857ffd chore: update README

gahow pushed to main at gahow/kvcache-simulator

2026-04-17 10:19:27 +00:00

cad83cec2f Merge branch 'feature/bucket-aware-routing'

43ada0cfc0 feat: add bucket score global router

b5a6fb964c feat: wire bucket identities through driver outputs

3a84c15068 fix: harden bucket routing review follow-up

fa381b5db3 feat: add bucketed service and strict global routing

Compare 12 commits »

gahow pushed to main at gahow/kvcache-simulator

2026-04-17 02:56:34 +00:00

82b3e2985f chore

gahow pushed to main at gahow/kvcache-simulator

2026-04-16 06:30:32 +00:00

67eef78244 chore: git ignore

gahow pushed to main at gahow/kvcache-simulator

2026-04-16 06:23:56 +00:00

996511f300 feat: new router and benchmark setup

gahow pushed to main at gahow/kvcache-simulator

2026-04-15 11:42:34 +00:00

c86d931d8f feat(ablate): input-length bucketing + auto-instance sizing

gahow pushed to main at gahow/kvcache-simulator

2026-04-15 11:08:14 +00:00

a3f386c858 feat: update ttft modeling and add cache affinity

ff316c6873 fix: cache calculation

Compare 2 commits »

gahow pushed to main at gahow/kvcache-simulator

2026-04-15 06:49:03 +00:00

365ceac3be chore: update ablation and clean configs

gahow pushed to main at gahow/kvcache-simulator

2026-04-14 07:46:47 +00:00

eaf574cd4e fix: kvcache evict workflow

663ca9c5b9 Support compute_dtype for FP4/FP8 tensor core FLOPS selection

84696604e8 Add B300 GPU preset and GLM-5-NVFP4 on 8xB300 config

Compare 3 commits »

gahow pushed to main at gahow/aituner

2026-04-14 02:27:09 +00:00

bf286ef2a6 docs: add qwen235b prefill 7-day compare

gahow pushed to main at gahow/kvcache-simulator

2026-04-14 02:22:40 +00:00

8d41123418 Update README with full feature documentation

gahow created branch main in gahow/kvcache-simulator

2026-04-13 17:17:05 +00:00

gahow pushed to main at gahow/kvcache-simulator

2026-04-13 17:17:05 +00:00

ec73a95e05 KVCache simulator for LLM serving cluster routing research