github ggml-org/llama.cpp b12577

latest releases: b12584, b12588, b12580...
pre-releaseone hour ago
Details

model : load ffn_gate_up_exps scales (#32657)

  • model: load ffn_gate_up_exps scales

The generic scale pass loads per-expert scales for ffn_gate_exps,
ffn_up_exps and ffn_down_exps but not for the merged ffn_gate_up_exps.
Load ffn_gate_up_exps_s there and expose it as ffn_up_exps_s when the layer
has no separate up tensor,
since build_moe_ffn applies up_exps_s to the
merged gate_up output. Inkling 2 now passes the expert scales to
build_moe_ffn like the other MoE models.

  • Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co

  • Update src/llama-model.h

Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co


Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co

Website:

Attestations:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

  • DISABLED
  • openEuler x86 (310p)
  • openEuler x86 (910b, ACL Graph)
  • openEuler aarch64 (310p)
  • openEuler aarch64 (910b, ACL Graph)

UI:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.