github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7375] use arm64 extensions ? #51199

New Issue
Open
opened 2026-04-28 18:54:24 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-28 18:54:24 -05:00
Owner
Copy Link

Originally created by @fxmbsw7 on GitHub (Oct 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7375

like neon64 and way others .. ?

greets ..

Originally created by @fxmbsw7 on GitHub (Oct 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7375 like neon64 and way others .. ? greets ..
GiteaMirror added the feature request label 2026-04-28 18:54:24 -05:00
GiteaMirror commented 2026-04-28 18:54:25 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Oct 27, 2024):

i added in llama.go in place of the -D arm .. int8 on arm8 -D__ARM_NEON64
and it didnt error out

<!-- gh-comment-id:2439824453 --> @fxmbsw7 commented on GitHub (Oct 27, 2024): i added in llama.go in place of the -D arm .. int8 on arm8 -D__ARM_NEON64 and it didnt error out
GiteaMirror commented 2026-04-28 18:54:26 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Oct 27, 2024):

( and u may know , new phones are not avx less )

<!-- gh-comment-id:2439826358 --> @fxmbsw7 commented on GitHub (Oct 27, 2024): ( and u may know , new phones are not avx less )
GiteaMirror commented 2026-04-28 18:54:26 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Oct 27, 2024):

i saw my snapdragon 8 gen 2 has bf16
and i8mm
i think this i8mm error is missing a package , with header files and stuff

the instructions and info via cpuinfo of my sd8g2 :
processor : 7 BogoMIPS : 38.40 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 asimdfhm dit uscat ilrcpc flagm ssbs sb paca pacg dcpodp flagm2 frint i8mm bf16 bti CPU implementer : 0x41 CPU architecture: 8 CPU variant : 0x1 CPU part : 0xd4e CPU revision : 0

<!-- gh-comment-id:2439921273 --> @fxmbsw7 commented on GitHub (Oct 27, 2024): i saw my snapdragon 8 gen 2 has bf16 and i8mm i think this i8mm error is missing a package , with header files and stuff the instructions and info via cpuinfo of my sd8g2 : processor : 7 BogoMIPS : 38.40 Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 asimdfhm dit uscat ilrcpc flagm ssbs sb paca pacg dcpodp flagm2 frint i8mm bf16 bti CPU implementer : 0x41 CPU architecture: 8 CPU variant : 0x1 CPU part : 0xd4e CPU revision : 0
GiteaMirror commented 2026-04-28 18:54:27 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Oct 27, 2024):

( the qcom docs say additionally )
Qualcomm® Hexagon™ Processor
• Fused AI Accelerator Architecture
• Hexagon Tensor Accelerator
• Hexagon Vector eXtensions
• Hexagon Scalar Accelerator
• Hexagon Direct Link
• Support for mix precision (INT8+INT16)
• Support for all precisions (INT4, INT8, INT16, FP16)
• Micro Tile Inferencing

i cant currently find if its less.than arm8.6 or newer

<!-- gh-comment-id:2439922886 --> @fxmbsw7 commented on GitHub (Oct 27, 2024): ( the qcom docs say additionally ) Qualcomm® Hexagon™ Processor • Fused AI Accelerator Architecture • Hexagon Tensor Accelerator • Hexagon Vector eXtensions • Hexagon Scalar Accelerator • Hexagon Direct Link • Support for mix precision (INT8+INT16) • Support for all precisions (INT4, INT8, INT16, FP16) • Micro Tile Inferencing i cant currently find if its less.than arm8.6 or newer
GiteaMirror commented 2026-04-28 18:54:29 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Oct 27, 2024):

an ai bot says its arm9
so the arm8.6 cmd in llama.go should work ?
ill try ..

<!-- gh-comment-id:2439923418 --> @fxmbsw7 commented on GitHub (Oct 27, 2024): an ai bot says its arm9 so the arm8.6 cmd in llama.go should work ? ill try ..
GiteaMirror commented 2026-04-28 18:54:30 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Oct 27, 2024):

look into -march=native -mcpu=native -mtune=native

<!-- gh-comment-id:2439925395 --> @fxmbsw7 commented on GitHub (Oct 27, 2024): look into -march=native -mcpu=native -mtune=native
GiteaMirror commented 2026-04-28 18:54:31 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Oct 27, 2024):

-m*=native and armv9 didnt work .. illegal operaton or instruction
armv8 worked
still testing on ..

<!-- gh-comment-id:2440018144 --> @fxmbsw7 commented on GitHub (Oct 27, 2024): -m*=native and armv9 didnt work .. illegal operaton or instruction armv8 worked still testing on ..
GiteaMirror commented 2026-04-28 18:54:32 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 5, 2024):

Take a look at #7199 which should help lay some foundation to make this a bit easier.

<!-- gh-comment-id:2458130728 --> @dhiltgen commented on GitHub (Nov 5, 2024): Take a look at #7199 which should help lay some foundation to make this a bit easier.
GiteaMirror commented 2026-04-28 18:54:32 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Nov 5, 2024):

looks good ?

On Tue, Nov 5, 2024, 21:53 Daniel Hiltgen @.***> wrote:

Take a look at #7199 https://github.com/ollama/ollama/pull/7199 which
should help lay some foundation to make this a bit easier.

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/7375#issuecomment-2458130728,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AJMLP3IDHFJBJKJKZSEHJKTZ7EV4FAVCNFSM6AAAAABQVCKKKSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDINJYGEZTANZSHA
.
You are receiving this because you authored the thread.Message ID:
@.***>

<!-- gh-comment-id:2458270555 --> @fxmbsw7 commented on GitHub (Nov 5, 2024): looks good ? On Tue, Nov 5, 2024, 21:53 Daniel Hiltgen ***@***.***> wrote: > Take a look at #7199 <https://github.com/ollama/ollama/pull/7199> which > should help lay some foundation to make this a bit easier. > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/7375#issuecomment-2458130728>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AJMLP3IDHFJBJKJKZSEHJKTZ7EV4FAVCNFSM6AAAAABQVCKKKSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDINJYGEZTANZSHA> > . > You are receiving this because you authored the thread.Message ID: > ***@***.***> >
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#51199
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?