Skip to content

v1.1.0 — Gemma 4 E2B support + prefill/decode kernel cycle

Choose a tag to compare

@ai-hpc ai-hpc released this 20 Jun 13:01
· 28 commits to main since this release
d07fee7

Adds Gemma 4 E2B support and a Gemma-4-focused kernel optimization cycle.
Gemma 4 runs greedy-identical to llama.cpp on Jetson Orin Nano Super (including
contexts past the 512-token sliding window). No change to the Qwen3 path
every optimization is env-gated.

Performance — Gemma 4 E2B Q4_K_M, Orin Nano Super (MAXN_SUPER)

Metric Before v1.1.0 Δ
Decode (tg) 12 tok/s 23.5 tok/s +96 % (llama.cpp parity)
Prefill (1261-tok) 152 tok/s 620 tok/s +308 % (4.1×)
Prefill (8192-tok) 63 tok/s 126 tok/s 2× (long-context collapse fixed)

Covers #96#101 (Gemma 4 support), #102#106 (decode parity), #117#128
(prefill cycle). See CHANGELOG.md for full notes.

Tag backfilled 2026-06-20 (release was merged via #129 but not tagged at the time).