Skip to content

Pull requests: ggml-org/ggml

New pull request New
39 Open 804 Closed
39 Open 804 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

CUDA/HIP: honor GGML_PREC_F32 in the flash-attention tile kernel
#1536 opened Jun 10, 2026 by RapidMark Loading…
1
sycl: fix soft_max_f32 max reduction
#1534 opened Jun 10, 2026 by someoneinjd Loading…
vulkan: add e4m3 (fp8) matmul for AMD RDNA4 — portable dequant default + opt-in native fp8
#1528 opened Jun 5, 2026 by RapidMark Loading…
4
metal : graceful failure instead of GGML_ABORT
#1527 opened Jun 3, 2026 by fiorelorenzo Loading…
perf(hip): enable -funsafe-math-optimizations for the ROCm backend
#1526 opened Jun 2, 2026 by RapidMark Loading…
1
ggml-cpu : fix soft_max_back wrong output when dst aliases src1 (y)
#1521 opened May 28, 2026 by devYRPauli Contributor Loading…
2
ggml : assert b->ne[3] == 1 in ggml_conv_transpose_2d_p0 (#1448)
#1520 opened May 28, 2026 by devYRPauli Contributor Loading…
2
ggml-cpu : fix rms_norm_back wrong output under in-place aliasing (#1491)
#1519 opened May 28, 2026 by devYRPauli Contributor Loading…
1
2
tests : add OLMoE-sized K-quant shapes to test_mul_mat_id (ref #1506)
#1518 opened May 28, 2026 by devYRPauli Contributor Loading…
2
Fix build and test running for Windows MSVC
#1512 opened May 26, 2026 by MaxwellGengYF Loading…
docs(gguf): extend Encoding slot to support percentage-mixed recipes
#1489 opened May 13, 2026 by mishig25 Contributor • Draft
1
ggml-cpu/riscv: gate cpu-riscv64 backend on Zv* sub-extensions
#1475 opened May 2, 2026 by mikey Loading…
opencl: add Adreno xmem attention fast path
#1461 opened Apr 19, 2026 by happyyzy Contributor Loading…
Update GGUF description to include full name
#1457 opened Apr 2, 2026 by mmontag Loading…
fix: gate AVX/AVX-512/AMX on OS XSAVE support via XGETBV
#1435 opened Mar 11, 2026 by Mattbusel Loading…
3
ggml-cpu: BMI2 is only available on amd64
#1392 opened Nov 26, 2025 by candrews Loading…
metal: implement cross-entropy and count-equal ops for MNIST
#1390 opened Nov 22, 2025 by xi-guo-0 Loading…
19
metal: accelerated conv2d
#1384 opened Nov 11, 2025 by bghira Contributor Loading…
1
ggml-cpu : Add GGML_CPU_FFAST_MATH for sine autovectorization
#1243 opened May 28, 2025 by danielzgtg Contributor • Draft
6
Temporary fix for rms norm backward on CPU.
#1197 opened Apr 22, 2025 by Alkamist Loading…
3
Update example readme/shell output for gpt-2-backend
#1159 opened Mar 26, 2025 by rememberlenny Loading…
1
Add an option not to abort on cuda OOM
#1110 opened Feb 11, 2025 by WilliamTambellini Contributor Loading…
37
ggml : add ggml_fft and ggml_ifft operator
#1105 opened Feb 6, 2025 by ilhamsyahids Loading…
3
ggml-cpu: use lookuptable for ggml op and parallelized some of the memcpy memset etc. calls before ggml_barriers
#1101 opened Feb 4, 2025 by Kamayuq Loading…
2
CUDA: update compilation flags for improved performance
#1099 opened Feb 3, 2025 by royshil Loading…
14
ProTip! Type g i on any issue or pull request to go back to the issue listing page.