LocalAI

mirror of https://github.com/mudler/LocalAI.git synced 2026-06-23 08:08:52 -04:00

Files

Ettore Di Giacinto 07985ba45b analysis: measured llama.cpp aggregate vs vLLM - already ~75-80% at npl<=128

llama-batched-bench Qwen3-32B-Q4_K_M: aggregate decode 235/391/540 t/s at
npl=32/64/128 vs vLLM 328/569/667 = 72/69/81%, multiplier 53x (vLLM 56x), still
climbing at 128. The 30x headline is wrong at realistic concurrency: llama.cpp is
ahead single-stream (MXFP4 1153 > 800) and ~75-80% aggregate. Aggregate prefill is
flat ~760 but GB10-compute-capped (vLLM ~800 too), so chunked prefill is a
latency/TTFT win not throughput; paged KV is the high-concurrency (thousands-seqs)
lever for vLLM's 24k regime. ROI: MXFP4 ship -> chunked prefill -> paged KV.

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

2026-06-21 11:32:40 +00:00

paged

analysis: measured llama.cpp aggregate vs vLLM - already ~75-80% at npl<=128

2026-06-21 11:32:40 +00:00

patches

bench(dense): root-cause the W4A4 NVFP4 hang; W4A16 vs Q4 is the headline

2026-06-20 06:59:50 +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: generic chat_template_kwargs (model config + per-request metadata) (#10359 )