vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : refactor online repacking (#10446)

Browse source 
* rename ggml-cpu-aarch64.c to .cpp

* reformat extra cpu backend.

- clean Q4_0_N_M and IQ4_0_N_M
  - remove from "file" tensor type
  - allow only with dynamic repack

- extract cpu extra bufts and convert to C++
  - hbm
  - "aarch64"

- more generic use of extra buffer
  - generalise extra_supports_op
  - new API for "cpu-accel":
     - amx
     - aarch64

* clang-format

* Clean Q4_0_N_M ref

Enable restrict on C++

* add op GGML_OP_MUL_MAT_ID for Q4_0_N_M with runtime repack

* added/corrected control on tensor size for Q4 repacking.

* Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* add debug logs on repacks.

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Djip007 2024-12-07 13:37:50 +01:00 • committed by GitHub
parent c2a16c0bdb
commit 19d8762ab6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 1136 additions and 1049 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Package.swift
View file

@ -10,14 +10,15 @@ var sources = [
"src/unicode.cpp",
"src/unicode-data.cpp",
"ggml/src/ggml.c",
"ggml/src/ggml-aarch64.c",
"ggml/src/ggml-alloc.c",
"ggml/src/ggml-backend.cpp",
"ggml/src/ggml-backend-reg.cpp",
"ggml/src/ggml-cpu/ggml-cpu.c",
"ggml/src/ggml-cpu/ggml-cpu.cpp",
"ggml/src/ggml-cpu/ggml-cpu-aarch64.c",
"ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp",
"ggml/src/ggml-cpu/ggml-cpu-hbm.cpp",
"ggml/src/ggml-cpu/ggml-cpu-quants.c",
"ggml/src/ggml-cpu/ggml-cpu-traits.cpp",
"ggml/src/ggml-threading.cpp",
"ggml/src/ggml-quants.c",
]