Ettore Di Giacinto 17855735c7 docs(paged): bf16 SSM-state build plan (PART C synthesis: edits, KL gate, bench, risks) ...

Synthesizes the bf16 SSM recurrent-state-cache plan into a build-agent brief:
ordered file-by-file edit list (kernel/op dtype-generic first, then cparams
default flip, gRPC/YAML, back-compat), the KL<1e-3 + PPL-delta + coherence +
long-context-drift acceptance gate that REPLACES the bit-exact md5 gate (bf16 is
intentionally non-bit-exact, equal precision to vLLM), bench targets (recurrence
3.98->2-3 ms/call, step 384->289-339 ms, 360-443 tok/s dense) + nsys check, the
default-bf16/f32-opt-out semantics + state-file back-compat, the risk register,
and the single biggest risk (silent corruption on the prefill/keep_rs_t/gather
paths) with the de-risk-first test-backend-ops step. Conv state stays f32 in v1.

Assisted-by: Claude:opus-4.8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-06-25 16:46:59 +00:00

..

ds4

chore: ⬆️ Update antirez/ds4 to 80ebbc396aee40eedc1d829222f3362d10fa4c6c (#10378)

2026-06-18 00:32:13 +02:00

grpc

fix: speedup git submodule update with --single-branch (#2847)

2024-07-13 22:32:25 +02:00

ik-llama-cpp

chore: ⬆️ Update ikawrakow/ik_llama.cpp to b3dfb7858cfcb9166e92f366e5af87f19ebc94be (#10395)

2026-06-19 00:03:37 +02:00

llama-cpp

docs(paged): bf16 SSM-state build plan (PART C synthesis: edits, KL gate, bench, risks)

2026-06-25 16:46:59 +00:00

privacy-filter

feat(pii): NER tier engine — privacy-filter.cpp backend + NER-centric PII filter (#10360)

2026-06-18 11:45:22 +01:00

turboquant

chore(turboquant): bump to 7d9715f1 + fix compilation against rebased fork (#10205)

2026-06-07 10:42:06 +02:00