Ettore Di Giacinto 362eea90ff docs(paged): fair re-run verdict - synthesize NVFP4 llama vs vLLM scorecard ...

Phase 3 synthesis of the max_prefill_tokens (patch 0013) fair re-run:
how much of the gap was prefill starvation, the genuine remaining gap
to vLLM, and where par-or-beat stands per concurrency/model.

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

2026-06-23 21:39:22 +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): fair re-run verdict - synthesize NVFP4 llama vs vLLM scorecard

2026-06-23 21:39:22 +00:00

CMakeLists.txt

fix(turboquant): resolve common.h by detecting llama-common vs common target (#9413)

2026-04-18 20:30:28 +02:00

grpc-server.cpp

feat(llama-cpp): per-model max_prefill_tokens option (chunked-prefill QoS budget)

2026-06-23 11:25:44 +00:00

Makefile

build(llama-cpp): isolate paged patches in patches/paged/ behind LLAMA_PAGED flag (default on)

2026-06-22 09:22:36 +00:00

package.sh

fix(llama.cpp): bundle libdl, librt, libpthread in llama-cpp backend (#9099)

2026-03-22 00:58:14 +01:00

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(rocm): bump to 7.x (#9323)

2026-04-12 08:51:30 +02:00