llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx
JakeATX/llamAmpere has 200 GitHub stars. It gained +10 stars over 1 recorded day in the last 7 days (snapshots through Oct 29, 2026).
Its biggest recent day was Oct 29, 2026, with +10 stars.
It currently ranks #47485 daily, #47423 weekly, #47832 monthly by momentum on Trending Repos; its best-ever rank is #6368.
Trending Repos first recorded it on Oct 12, 2026.
| Date | Stars gained | Total stars | Forks gained |
|---|---|---|---|
| +10 | 200 | +1 |