Commit History
E2B pf64 at cap 131,072 — the checkpoint's own max_position_embeddings 1ec5c73 verified
model card: standard structure, measured facts, verified license declarations 0d7b6cb verified
README: ring3 per-layer-type SDPA bundles 15c2afa verified
Add ring3 gemma4_e2b_qat_decode_int4lin_tbl_pf64_ring_c2048_gqafull 0d2065c verified
Add ring3 gemma4_e2b_qat_decode_int4lin_tbl_pf64_ring_c4096_gqafull f62c233 verified
Add ring3-smoke gemma4_e2b_qat_decode_int4lin_tbl_pf64_ring_c4096_gqafull_l5 f1485ac verified
README: ring2 capacity-ladder bundles 023e7a0 verified
Add ring2 gemma4_e2b_qat_decode_int4lin_tbl_pf64_ring_c8192 9030ad4 verified
Add ring2 gemma4_e2b_qat_decode_int4lin_tbl_pf64_ring_c2048 37f9a33 verified
Add ring2-smoke gemma4_e2b_qat_decode_int4lin_tbl_pf64_ring_c2048_l5 2fedcea verified
README: ring bundles cb38966 verified
Add ring gemma4_e2b_qat_decode_int4lin_tbl_pf64_ring_c16384 9f5ec84 verified
README: ring-smoke bundles beecbbf verified
Add ring-smoke gemma4_e2b_qat_decode_int4lin_tbl_pf64_ring_c16384_l5 6d4e0b3 verified
docs: stable/ measured — memory fix confirmed, capacity-16384 decode cost makes it non-deployable as shipped 54f007f verified
prune: remove superseded/non-functional artifacts 5005b4c verified
prune: remove superseded/non-functional artifacts 73bef81 verified
docs: stable/ folders in Status, oracle verification line, known-issue points at available fix 98d2913 verified
README: stable bundles 50c2ae0 verified
Add stable gemma4_e2b_qat_decode_int4lin_tbl_pf64_stable_c16384 4591f92 verified
README: stable-smoke bundles 25b51a7 verified
Add stable-smoke gemma4_e2b_qat_decode_int4lin_tbl_pf64_stable_c16384_l5 bd55b68 verified
docs: correct known-issue mechanism (shape-signature specialization cache, guided affected equally at depth) 1d86775 verified
docs: refresh measured performance (local retest 2026-08-18) 81c2abf verified
docs: descriptive model card 60bc67d verified
Ben Graville commited on
README: w4a8 bundles 03102f0 verified
Ben Graville commited on
Add w4a8/gemma4_e2b_qat_decode_int4lin_a8_tbl_pf64 1563877 verified
Ben Graville commited on
add missing chat_template.jinja to gpu-pipelined/gemma4_e2b_qat_decode_int4lin_tbl_pf64/tokenizer (additive fix, bundle otherwise untouched) b1b5044 verified
Ben Graville commited on
add missing chat_template.jinja to gpu-pipelined/gemma4_e2b_qat_decode_int4lin_tbl/tokenizer (additive fix, bundle otherwise untouched) 2a59909 verified
Ben Graville commited on
Add PLE gather_raw table sidecar 9cde3bf verified
Ben Graville commited on
README: ctx16384 bundles 8a0128c verified
Ben Graville commited on
Add ctx16384 gemma4_e2b_qat_decode_int4lin_tbl_pf64 38150d1 verified
Ben Graville commited on
README: ctx8192 bundles 8a3f3be verified
Ben Graville commited on
Add ctx8192 gemma4_e2b_qat_decode_int4lin_tbl_pf64 c2524f8 verified
Ben Graville commited on
Add gemma4_e2b_qat_decode_int4lin_tbl_pf64 a791d48 verified
Ben Graville commited on
Add gemma4_e2b_qat_decode_int4lin_tbl 9ad2f9f verified
Ben Graville commited on
Upload README.md with huggingface_hub de7f65f verified
Ben Graville commited on
initial commit 1a19324 verified
Ben Graville commited on