Ettore Di Giacinto 00f92659f8 docs(paged): correct vLLM recurrent-state precision (f32, not bf16) ...

Earlier text claimed bf16 = vLLM's own precision; that was a refuted byte-gate
draft re-surfacing. The settled finding (BITEXACT_VS_VLLM.md, proven 3 ways) is
that vLLM keeps the gated-DeltaNet TEMPORAL state in f32 (only its conv state is
bf16). So bf16 temporal is BELOW vLLM's recurrent precision, not a match; and at
equal f32 precision llama's recurrence already beats vLLM (84.6% vs 82.4% peak).

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

2026-06-26 06:22:08 +00:00

..

paged

feat(paged): target-readiness for 2xH200 - correctness PASS, load-gen harness, projection

2026-06-21 23:16:28 +00:00

patches

docs(paged): correct vLLM recurrent-state precision (f32, not bf16)

2026-06-26 06:22:08 +00:00

CMakeLists.txt

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

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

grpc-server.cpp

Merge branch 'master' into worktree-feat+paged-attention

2026-06-25 21:56:35 +00:00

Makefile

Merge branch 'master' into worktree-feat+paged-attention

2026-06-25 21:56:35 +00:00

package.sh

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

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

prepare.sh

fix(llama-cpp/paged): stop double-applying the paged patches in prepare.sh

2026-06-22 11:54:51 +00:00

run.sh

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

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