Skip to content

merge from upstream #74

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 201 commits into from
Jul 7, 2025
Merged

merge from upstream #74

merged 201 commits into from
Jul 7, 2025

Conversation

@l3utterfly
Copy link
Owner

No description provided.

jeffzhou2000 added 30 commits July 6, 2025 22:06
@jeffzhou2000
ggml-qnn: add Qualcomm QNN backend for GGML
f190e4f
@jeffzhou2000
ggml-qnn: santiy check
e3a54bf
@jeffzhou2000
ggml-qnn: update script build-run-android.sh to compare peformance of…
824ac72 
… ggml-qnn
@jeffzhou2000
ggml-qnn: fix minor issue in test-backend-ops.cpp
428a6f4
@jeffzhou2000
ggml-qnn: merge QNN RPC feature from https://github.com/zhouwg/kantv/…
1763ec5 
…blob/ggml-qnn-quantize/core/ggml/llamacpp/ggml-qnn.cpp
@jeffzhou2000
ggml-qnn: sync from branch kantvai-ggmlqnn-npurpc
db2985a
@jeffzhou2000
ggml-qnn: a concise approach to offload mulmat to QNN backend(sync fr…
0ade459 
…om branch kantvai-ggmlqnn-npurpc, https://github.com/kantv-ai/llama.cpp/wiki/offloading-mulmat-to-QNN-backend)
@jeffzhou2000
ggml-qnn: remove redundant codes
27af242
@jeffzhou2000
ggml-qnn: sync from branch kantvai-ggmlqnn-npurpc
3251453
@jeffzhou2000
ggml-qnn: sync from branch kantvai-ggmlqnn-npurpc
1dfb4d6
@jeffzhou2000
ggml-qnn: sync from branch kantvai-ggmlqnn-npurpc
fffb616
@jeffzhou2000
ggml-qnn: add Qualcomm QNN backend for GGML
9b54d7b
@jeffzhou2000
ggml-qnn: merge QNN RPC feature from https://github.com/zhouwg/kantv/…
8cfe5e3 
…blob/ggml-qnn-quantize/core/ggml/llamacpp/ggml-qnn.cpp
@jeffzhou2000
ggml-qnn: sync from branch kantvai-ggmlqnn-npurpc
496a5fa
@jeffzhou2000
ggml-qnn: a concise approach to offload mulmat to QNN backend(sync fr…
386010a 
…om branch kantvai-ggmlqnn-npurpc, https://github.com/kantv-ai/llama.cpp/wiki/offloading-mulmat-to-QNN-backend)
@jeffzhou2000
ggml-qnn: remove redundant codes
b8b3310
@jeffzhou2000
ggml-qnn: sync from branch kantvai-ggmlqnn-npurpc
6f777fd
@jeffzhou2000
ggml-qnn: sync from branch kantvai-ggmlqnn-npurpc
a6dd130
@jeffzhou2000
ggml-qnn: sync from branch kantvai-ggmlqnn-npurpc
5d8e9b9
@jeffzhou2000
ggml-qnn: fix a minior typo in internal doc
27d165e
@jeffzhou2000
ggml-qnn: refine function ggml_qnn_create_general_tensor() to avoid c…
f3b8449 
…omplex/redundant pointer operation
@jeffzhou2000
ggml-qnn: fix a minor typo in source code
398fea7
@jeffzhou2000
build: avoid ggml-qnn backend breaking other backend's builds
c81d308
@jeffzhou2000
ggml-qnn: remove redundant codes to make PR reviewers happy
122df52
@jeffzhou2000
ggml-qnn: refine code format
bd9a573
@jeffzhou2000
ggml-qnn: offload quantized type mulmat to QNN backend
1ecc448
@jeffzhou2000
ggml-qnn: refine source code structure to make code more clearly
ba0878d
@jeffzhou2000
ggml-qnn: enable release build with necessary logs to make reviewers …
1f9c1e3 
…happy
@jeffzhou2000
ggml-qnn: enable all quantize type with 2d mulmat
a3bf24f
@jeffzhou2000
ggml-qnn: enable log output of GGMLQNN_LOG_INFO in command line mode …
d2bb13f 
…for benchmark more conveniently
jeffzhou2000 added 24 commits July 6, 2025 22:06
@jeffzhou2000
project: sync with upstream
9c0dd2f
@jeffzhou2000
project: sync with upstream
6028dd7
@jeffzhou2000
test: verify Google gemma-3n on Android phone
7c9b099
@jeffzhou2000
project: release libggmldsp-skel.so v0.98.8
4be1358
@jeffzhou2000
project: sync with upstream(adapt to PR-14158 in the upstream)
5eb8d90
@jeffzhou2000
ggml-hexagon: add ggmlhexagon-testops.cpp
ce1ad4c
@jeffzhou2000
script: update copyright info of scripts/build-run-android.sh
a3026b4
@jeffzhou2000
ggml-hexagon: upgrade QNN SDK to v2.36.0.250627
3f8aa70
@jeffzhou2000
ggml-hexagon: modify default mulmat_algotype from 0 to 32
6a67b64
@jeffzhou2000
ggml-hexagon: forward compatible with Qualcomm's new SDK
b8a47ee
@jeffzhou2000
project: sync with upstream
bcecdfd
@jeffzhou2000
project: sync with upstream(PR-14501:remove kompute backend)
d14a9a0
@jeffzhou2000
script: add MiniCPM4-0.5B-F32.gguf in build-run-android.sh
a4ca5f6
@jeffzhou2000
ggml:fix minior issue during rebase upstream PR-14501: remove kompute…
b299aa3 
… backend
@jeffzhou2000
project: sync with upstream
6bdef2e
@jeffzhou2000
script: add build-run-ggmlopencl-android.sh
d081d22
@jeffzhou2000
build: refine build-run-ggmlopencl-android.sh and build-run-ggmlhexag…
584bc48 
…on-android.sh
@jeffzhou2000
script: update copyright info in build-run-ggmlopencl-android.sh
753844b
@jeffzhou2000
script: add build-run-ggmlvulkan-android.sh
30b5589
@jeffzhou2000
script: update copyright info in build-run-ggmlvulkan-android.sh
cc82661
@jeffzhou2000
script: fix a minior regression in build-run-ggmlhexagon-android.sh
c41f7c1
@jeffzhou2000
ggml-hexagon: apply similar logic as in ggml-vulkan
973948b
@jeffzhou2000
script: refine build-run-ggmlhexagon-android.sh
00ca48b
@jeffzhou2000
ggml-hexagon: refine format
9cedcc6
@l3utterfly l3utterfly merged commit 6770d15 into l3utterfly:ggml-hexagon Jul 7, 2025
28 of 47 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

build examples ggml script testing

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@l3utterfly @jeffzhou2000