Skip to content

sync : ggml #3108

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

Merged
merged 16 commits into from
May 1, 2025
Merged

sync : ggml #3108

Changes from 1 commit
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
fc0c187
ggml : fix ggml_gallocr_ptr type (ggml/1205)
slaren Apr 30, 2025
fd0ca81
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (llama…
rgerganov Apr 25, 2025
abb24a6
change the reorder tensor from init to execute OP (llama/13003)
NeoZhangJianyu Apr 25, 2025
123bf28
ggml: move fp16/bf16 conversion optimizations to CPU backend + export…
SongXiaoXi Apr 26, 2025
3c7e3af
musa: fix build warning (llama/13129)
yeahdongcn Apr 27, 2025
32b93f5
CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (llama/13137)
JohannesGaessler Apr 28, 2025
74f09c4
musa: fix typo in cc control (llama/13144)
yeahdongcn Apr 28, 2025
b89f84f
SYCL: Add all missing unary kernels (llama/13074)
qnixsynapse Apr 28, 2025
fa4d6b4
fix(rpc): Improve input validation and error handling (llama/13069)
thevilledev Apr 28, 2025
16121dc
CUDA: fix non-cont. inputs for batched mat mul (llama/13155)
JohannesGaessler Apr 29, 2025
cd8054f
feat(ggml-cpu): enable z17 compile (llama/13182)
taronaeo Apr 30, 2025
80dd958
ggml : fix ppc64le build (llama/13176)
shalinib-ibm Apr 30, 2025
4d38d02
vulkan: use uint array index to avoid glslang bug (llama/13193)
jeffbolznv Apr 30, 2025
cd618ce
CUDA: batched+noncont MMQ, refactor bs>1 MoE code (llama/13199)
JohannesGaessler Apr 30, 2025
16b5022
sync : ggml
ggerganov May 1, 2025
842678b
talk-llama : sync llama.cpp
ggerganov May 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
ggml : fix ppc64le build (llama/13176) 
Build fails with compilation error on power pc.
This patch fixes the same.

Tested with unit tests run via
 --build <build_dir> && cd <build_dir> && make test

Signed-off-by: Shalini Salomi Bodapati <[email protected]>
  • Loading branch information
@shalinib-ibm @ggerganov
shalinib-ibm authored and ggerganov committed May 1, 2025
commit 80dd958f918b31f8c6849019a78fc58efbb3cd8b
2 changes: 1 addition & 1 deletion ggml/src/ggml-cpu/simd-mappings.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -341,7 +341,7 @@ static inline void __avx_f32cx8_store(ggml_fp16_t *x, __m256 y) {
#define GGML_F32_EPR 4

#define GGML_F32x4 vector float
#define GGML_F32x4_ZERO 0.0f
#define GGML_F32x4_ZERO {0.0f}
#define GGML_F32x4_SET1 vec_splats
#define GGML_F32x4_LOAD(p) vec_xl(0, p)
#define GGML_F32x4_STORE(p, r) vec_xst(r, 0, p)
Expand Down