]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (llama...
authorDavid Huang <redacted>
Sun, 11 May 2025 12:18:39 +0000 (20:18 +0800)
committerGeorgi Gerganov <redacted>
Tue, 13 May 2025 10:59:21 +0000 (13:59 +0300)
commite1b2ace0f8852b529cb23dee087aacad749a38b4
tree1cd53e16aeee56ab48bc1910ea0e59a31868e45f
parent6db0e01db69f9cc1bc7d5b17f18fad3eb672eed0
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (llama/13386)
ggml/include/ggml-backend.h
ggml/src/ggml-backend.cpp