Commits

History for

ondev-pad-reflect

Commits on Jun 15, 2024

move BLAS to a separate backend (llama/6210)

slaren
and
ggerganov
committedJun 15, 2024
Update Vulkan RoPE implementation (llama/7818)

authored and
ggerganov
committedJun 15, 2024
llama : offload to RPC in addition to other backends (llama/7640)

authored and
ggerganov
committedJun 15, 2024
fix bug introduced in using calloc (llama/7701)

airlied
authored and
ggerganov
committedJun 15, 2024

Commits on May 11, 2024

ggml : fix calloc argument ordering. (llama/6820)

airlied
authored and
ggerganov
committedMay 11, 2024

Commits on Mar 27, 2024

backend : offload large batches to GPU (llama/6083)

authored and
ggerganov
committedMar 27, 2024

Commits on Mar 18, 2024

alloc : fix allocation data of pre-allocated leafs

slaren
authored and
ggerganov
committedMar 18, 2024

Commits on Mar 14, 2024

llama : add pipeline parallelism support (llama/6017)

committedMar 14, 2024

Commits on Feb 19, 2024

ggml : add ALiBi support for ggml_soft_max_ext (llama/5488)
ggerganov
committedFeb 19, 2024

Commits on Feb 12, 2024

ggml-alloc : allocate all leafs as if they were inputs (ggerganov#731 )
slaren
committedFeb 12, 2024

Commits on Feb 11, 2024

ggml-alloc : v3 (ggerganov#727 )
slaren
committedFeb 11, 2024

Commits on Jan 30, 2024

ggml alloc: Fix for null dereference on alloc failure (llama/5200)

ptsochantaris
authored and
ggerganov
committedJan 30, 2024

Commits on Jan 28, 2024

ggml : add Vulkan backend (llama/2059)

committedJan 28, 2024

Commits on Jan 27, 2024

ggml-alloc : add 10% margin to the buffer sizes (llama/5149)

slaren
authored and
ggerganov
committedJan 27, 2024
llama : pre-allocate input tensors in a separate buffer (llama/5100)

slaren
authored and
ggerganov
committedJan 27, 2024

Commits on Jan 12, 2024

llama : ggml-backend integration (llama/4766)

committedJan 12, 2024

Commits on Dec 22, 2023

sync : llama.cpp (ggml_scale, ggml_row_size, ggml_mul_mat_set_prec) (ggerganov#662 )

committedDec 22, 2023

Commits on Dec 7, 2023

sync : llama.cpp (fused soft max, gpu cpy ops, etc.) (ggerganov#640 )

ggerganov
and
slaren
committedDec 7, 2023

Commits on Nov 30, 2023

ggml-backend update: buffer types, backend registry, graph compare, tests (ggerganov#620 )

slaren
and
ggerganov
committedNov 30, 2023

Commits on Nov 13, 2023

sync : llama.cpp (CUDA ReLU, CPU-only with CUDA, bloom fix, etc) (ggerganov#607 )
ggerganov
committedNov 13, 2023

Commits on Oct 30, 2023

ggml-backend v2 : add ggml_backend_sched (ggerganov#586 )

slaren
and
ggerganov
committedOct 30, 2023

Commits on Oct 9, 2023

Disable ggml-alloc assert for CPU version of Sam.cpp if the view doesn't have a buffer (ggerganov#562 )
Yavor Ivanov
committedOct 9, 2023

Commits on Oct 7, 2023

ggml-alloc : fix crash when used without ggml-backend (ggerganov#555 )
slaren
committedOct 7, 2023

Commits on Oct 6, 2023

ggml backends interface v1 (ggerganov#547 )

slaren
and
ggerganov
committedOct 6, 2023

Commits on Oct 4, 2023

sync : llama.cpp (training, refactoring) (ggerganov#548 )
ggerganov
committedOct 4, 2023

Commits on Sep 15, 2023

sync : whisper.cpp (Metal + ggml sched_yield fix + reduce ggml-alloc size) (ggerganov#522 )
ggerganov
committedSep 15, 2023

Commits on Sep 8, 2023

sync : whisper (POSIX) (ggerganov#511 )
ggerganov
committedSep 8, 2023

Commits on Sep 5, 2023

ggml : sync llama.cpp (view_src + alloc improvements) (ggerganov#504 )
ggerganov
committedSep 5, 2023

Commits on Aug 28, 2023

sam : use ggml-alloc (ggerganov#490 )
Yavor Ivanov
committedAug 28, 2023
ggml : sync llama.cpp (gguf + metal + ROCm + etc.) (ggerganov#489 )
ggerganov
committedAug 28, 2023
ggml : sync with sam.cpp (add SAM Vit H & L model support and fix SAM's output) (ggerganov#476 )
Yavor Ivanov
committedAug 28, 2023

Commits on Aug 22, 2023

ggml : sync latest llama.cpp (GGUF) (ggerganov#470 )
ggerganov
committedAug 22, 2023

Commits on Aug 16, 2023

ggml : backport ggml-alloc from llama.cpp (ggerganov#433 )

smspillaz
and
slaren
committedAug 16, 2023

Loading