llama.cpp
vulkan: implement several ops relevant for ggml_opt
#11769
Merged

vulkan: implement several ops relevant for ggml_opt #11769

remyoudompheng
github-actions github-actions added testing
github-actions github-actions added Vulkan
github-actions github-actions added ggml
0cc4m
0cc4m commented on 2025-02-10
jeffbolznv
jeffbolznv commented on 2025-02-13
0cc4m
remyoudompheng
jeffbolznv
jeffbolznv commented on 2025-02-15
remyoudompheng remyoudompheng force pushed 1 year ago
jeffbolznv
jeffbolznv approved these changes on 2025-02-16
netrunnereve
remyoudompheng vulkan: support memset_tensor
dca13cbe
remyoudompheng vulkan: support GGML_OP_SUM
9de61b5b
remyoudompheng vulkan: implement GGML_OP_ARGMAX
f354a781
remyoudompheng vulkan: implement GGML_OP_SUB
eacca58d
remyoudompheng vulkan: implement GGML_OP_COUNT_EQUAL
7a6cb87e
remyoudompheng vulkan: implement GGML_OP_OPT_STEP_ADAMW
750e1a4c
remyoudompheng vulkan: fix check_results RWKV_WKV6 crash and memory leaks
6f58276f
remyoudompheng vulkan: implement GGML_OP_REPEAT_BACK
49080311
remyoudompheng tests: remove invalid test-backend-ops REPEAT_BACK tests
e22079cc
remyoudompheng vulkan: fix COUNT_EQUAL memset using a fillBuffer command
e172d2d9
remyoudompheng remyoudompheng force pushed to e172d2d9 1 year ago
remyoudompheng
0cc4m
0cc4m approved these changes on 2025-02-17
0cc4m 0cc4m merged 2eea03d8 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone