sync : ggml#3880

Merged

ggerganov merged 22 commits into

masterfrom

sync-ggml-26-06-15

Jun 15, 2026

Commits on Jun 15, 2026

cuda: reset cuda context after reading memory size (llama/23935)

0cc4m
authored and
ggerganov
committed
vulkan: Use cm2 decode_vector for mul_mat_id B matrix loads (llama/23991)

jeffbolznv
authored and
ggerganov
committed
Implement 2D workgroups for scale, binary, and unary ops (llama/24044)

nikhilJain17
authored and
ggerganov
committed
Handle buffer overlap / buffer aliasing for concat operator (llama/24000)

authored and
ggerganov
committed
ggml-webgpu: Improve prefill speeds for k-quants + refactor matmul for Q4/Q5/Q8 and k-quants (llama/24225)

yomaytk
authored and
ggerganov
committed
ggml-webgpu: Add clang-format job (llama/24308)

reeselevine
authored and
ggerganov
committed
Remove case for GGML_TYPE_Q4_K in mvvq.cu (llama/23528)

ravel7524
authored and
ggerganov
committed
ggml-cpu : fix rms_norm_back wrong output under in-place aliasing (llama/24305)

devYRPauli
and
ggerganov
committed
ggml : add GGML_OP_COL2IM_1D (llama/24206)

ServeurpersoCom
authored and
ggerganov
committed
vulkan: add `v_dot2_f32_f16` support in matrix-matrix multiplication and Flash Attention (llama/24123)

0cc4m
authored and
ggerganov
committed
vulkan: reduce iq1 shared memory usage for mul_mm (llama/24287)

jeffbolznv
authored and
ggerganov
committed
CUDA: Fix ssm_scan_f32 data-races (llama/24360)

ORippler
authored and
ggerganov
committed
Remove padding and multiple D2D copies for MTP (llama/24086)

gaugarg-nv
authored and
ggerganov
committed
vulkan: use medium matmul tile on Asahi Linux (llama/24306)

xingjianll
authored and
ggerganov
committed
vulkan: add fast path for contiguous buffer transfers (llama/23973)

winstonma
authored and
ggerganov
committed
ggml : bump version to 0.15.0 (ggml/1539)
ggerganov
committed
vulkan: ifdef eMesaHoneykrisp (build fix) (llama/24479)

jeffbolznv
authored and
ggerganov
committed
opencl: add q5_0/q5_1 gemm and gemv kernels for Adreno (llama/24319)

authored and
ggerganov
committed
ggml: support concat for scalar types at cuda backend (llama/24011)

zihaomu
authored and
ggerganov
committed
ggml : bump version to 0.15.1 (ggml/1541)
ggerganov
committed
sync : ggml
ggerganov
committed
talk-llama : sync llama.cpp
ggerganov
committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

sync : ggml#3880

sync : ggml#3880
ggerganov merged 22 commits into
masterfrom
sync-ggml-26-06-15

Commits on Jun 15, 2026

cuda: reset cuda context after reading memory size (llama/23935)

vulkan: Use cm2 decode_vector for mul_mat_id B matrix loads (llama/23991)

Implement 2D workgroups for scale, binary, and unary ops (llama/24044)

Handle buffer overlap / buffer aliasing for concat operator (llama/24000)

ggml-webgpu: Improve prefill speeds for k-quants + refactor matmul for Q4/Q5/Q8 and k-quants (llama/24225)

ggml-webgpu: Add clang-format job (llama/24308)

Remove case for GGML_TYPE_Q4_K in mvvq.cu (llama/23528)

ggml-cpu : fix rms_norm_back wrong output under in-place aliasing (llama/24305)

ggml : add GGML_OP_COL2IM_1D (llama/24206)

vulkan: add `v_dot2_f32_f16` support in matrix-matrix multiplication and Flash Attention (llama/24123)

vulkan: reduce iq1 shared memory usage for mul_mm (llama/24287)

CUDA: Fix ssm_scan_f32 data-races (llama/24360)

Remove padding and multiple D2D copies for MTP (llama/24086)

vulkan: use medium matmul tile on Asahi Linux (llama/24306)

vulkan: add fast path for contiguous buffer transfers (llama/23973)

ggml : bump version to 0.15.0 (ggml/1539)

vulkan: ifdef eMesaHoneykrisp (build fix) (llama/24479)

opencl: add q5_0/q5_1 gemm and gemv kernels for Adreno (llama/24319)

ggml: support concat for scalar types at cuda backend (llama/24011)

ggml : bump version to 0.15.1 (ggml/1541)

sync : ggml

talk-llama : sync llama.cpp