Ben Graville commited on
Commit
18a972a
·
verified ·
1 Parent(s): 642c556

README: ctx8192 bundles

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -27,3 +27,14 @@ below; all original model licences apply and travel with these weights.
27
  - Bundles carry `runtime_env COREAI_CHUNK_THRESHOLD=1`.
28
 
29
  Upstream sources: `google/gemma-4-E4B-it-qat-q4_0-unquantized`
 
 
 
 
 
 
 
 
 
 
 
 
27
  - Bundles carry `runtime_env COREAI_CHUNK_THRESHOLD=1`.
28
 
29
  Upstream sources: `google/gemma-4-E4B-it-qat-q4_0-unquantized`
30
+
31
+
32
+ ## High-context bundles — ctx 8192
33
+
34
+ Same weights, same graph, same recipe as the 4096 bundles above — the exporter's
35
+ `--max-ctx` only widens the dynamic sequence bound and the manifest's
36
+ `language.max_context_length`. KV cache stays fp16.
37
+
38
+ | Bundle | Source checkpoint | Context | Functions | KV dtype | Producer | Created |
39
+ |---|---|---|---|---|---|---|
40
+ | `ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64` | google/gemma-4-E4B-it-qat-q4_0-unquantized | 8192 | main+prefill | fp16 | coreai-core 1.0.0b2 | 20260817T204459Z |