Ettore Di Giacinto 634c0e5a0f docs(paged): rms_norm->fp4 fold analysis - bit-exact decode ceiling at 95% of vLLM ...

The standalone quantize fold is empirically flat (Lever-2 precedent) with the
worst gain/plumbing ratio; no bit-exact lever remains. Dense 371.81 t/s @npl128
= 95.0% of vLLM 391, recurrence past vLLM at the LPDDR5x DRAM floor, all
byte-identical to llama f32. Only bf16 state (shelved) goes further.

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

2026-06-25 22:42:08 +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 d5507e33ae7ee2b7b41475f08044d3bde3b839ee (#10498)

2026-06-25 00:57:42 +02:00

llama-cpp

docs(paged): rms_norm->fp4 fold analysis - bit-exact decode ceiling at 95% of vLLM

2026-06-25 22:42:08 +00:00

privacy-filter

chore: ⬆️ Update localai-org/privacy-filter.cpp to 98f52c5ef2250f207cc6b9a6aef05393a120cb7c (#10394)

2026-06-20 01:37:21 +02:00

turboquant

feat: single-build ggml CPU_ALL_VARIANTS for llama-cpp + turboquant (x86/arm64/apple) (#10497)

2026-06-25 15:47:03 +02:00