Ettore Di Giacinto d2651c86d9 bench(dense): root-cause the W4A4 NVFP4 hang; W4A16 vs Q4 is the headline ...

Researched: W4A4 hangs on GB10 because FlashInfer ships no FP4 cubins for
sm_120/121 (all datacenter Sm100a); dense mm_fp4 is gated-off/returns-zeros on
consumer Blackwell, and the FlashInfer FP4 autotuner spins on the first forward
pass. Not a misconfig - dense W4A4 inference isn't validated on sm_121. W4A16
(4-bit weight / 16-bit act, Marlin) vs llama Q4_K_M is the correct apples-to-
apples (same quant class) AND the fast path. Removed the misleading 'W4A4 would
be faster / lower bound' framing. Sources: vllm #30163/#26381, flashinfer
#2577/#3294, cutlass #3096.

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

2026-06-20 06:59:50 +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

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

2026-06-20 06:59:50 +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