vulkan: implement several ops relevant for ggml_opt #11769
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
testing
0cc4m
reviewed
Feb 10, 2025
jeffbolznv
reviewed
Feb 14, 2025
| for (uint i2 = i12; i2 < p.ne02; i2 += p.ne12) { | ||
| for (uint i1 = i11; i1 < p.ne01; i1 += p.ne11) { | ||
| for (uint i0 = i10; i0 < p.ne00; i0 += p.ne10) { | ||
| acc += data_a[i3*p.nb03 + i2*p.nb02 + i1*p.nb01 + i0*p.nb00]; |
There was a problem hiding this comment.
Is get_aoffset() needed here? (I don't know)
|
The Intel crash can be ignored. Once you resolve the memset, this can be merged. |
|
Thanks for the review |
jeffbolznv
reviewed
Feb 15, 2025
remyoudompheng
force-pushed
the
vulkan-ggmlopt-pr
branch
from
3d506e5 to
34792b3
Compare
jeffbolznv
approved these changes
Feb 16, 2025
|
The tests are passing for me on GCN. It would definitely be cool to be able to do some finetuning on Vulkan once GGML gets training support. |
remyoudompheng
force-pushed
the
vulkan-ggmlopt-pr
branch
from
b94a44c to
e172d2d
Compare
|
rebased branch to resolve conflicts in |
0cc4m
approved these changes
Feb 17, 2025
orca-zhang
pushed a commit
to orca-zhang/llama.cpp
that referenced
this pull request
Feb 26, 2025
* vulkan: support memset_tensor * vulkan: support GGML_OP_SUM * vulkan: implement GGML_OP_ARGMAX * vulkan: implement GGML_OP_SUB * vulkan: implement GGML_OP_COUNT_EQUAL * vulkan: implement GGML_OP_OPT_STEP_ADAMW * vulkan: fix check_results RWKV_WKV6 crash and memory leaks * vulkan: implement GGML_OP_REPEAT_BACK * tests: remove invalid test-backend-ops REPEAT_BACK tests * vulkan: fix COUNT_EQUAL memset using a fillBuffer command
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Feb 26, 2025
* vulkan: support memset_tensor * vulkan: support GGML_OP_SUM * vulkan: implement GGML_OP_ARGMAX * vulkan: implement GGML_OP_SUB * vulkan: implement GGML_OP_COUNT_EQUAL * vulkan: implement GGML_OP_OPT_STEP_ADAMW * vulkan: fix check_results RWKV_WKV6 crash and memory leaks * vulkan: implement GGML_OP_REPEAT_BACK * tests: remove invalid test-backend-ops REPEAT_BACK tests * vulkan: fix COUNT_EQUAL memset using a fillBuffer command
mglambda
pushed a commit
to mglambda/llama.cpp
that referenced
this pull request
Mar 8, 2025
* vulkan: support memset_tensor * vulkan: support GGML_OP_SUM * vulkan: implement GGML_OP_ARGMAX * vulkan: implement GGML_OP_SUB * vulkan: implement GGML_OP_COUNT_EQUAL * vulkan: implement GGML_OP_OPT_STEP_ADAMW * vulkan: fix check_results RWKV_WKV6 crash and memory leaks * vulkan: implement GGML_OP_REPEAT_BACK * tests: remove invalid test-backend-ops REPEAT_BACK tests * vulkan: fix COUNT_EQUAL memset using a fillBuffer command
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR implements several GGML opcodes which are possibly relevant for #10544 (SUM, ARGMAX, SUB, COUNT_EQUAL, OPT_STEP_ADAMW, REPEAT_BACK).
After these patches, it is possible to run
test-optusing the Vulkan backend (with a few failures maybe caused by rounding issues?).Several issues were identified in test-backend-ops:
-b CPU)Several issues were identified in Vulkan CHECK_RESULTS mode: