ochafik/llama.cpp

Pull Requests Commits

build: apply MSVC /bigobj option to c/cpp files only (#11423)

jeffbolznv committed 1 year ago

Verified f35726c2

vulkan: compile shaders on-demand (#11406)

jeffbolznv committed 1 year ago

Verified 4a75d193

Hip: disable VMM on hip as it seams that it dosent work in some configurations (#11420)

IMbackK committed 1 year ago

Verified 26771a14

build: add /bigobj to MSVC build (#11407)

jeffbolznv committed 1 year ago

Verified ca6baf76

docker : add GGML_CPU_ARM_ARCH arg to select ARM architecture to build for (#11419)

slaren committed 1 year ago

Verified 6e264a90

server : fix cleaning up stream task (#11418)

ngxson committed 1 year ago

Verified 49b0e3ce

docker : fix CPU ARM build (#11403)

slaren committed 1 year ago

Verified 20a75815

ci : fix line breaks on windows builds (#11409)

ggerganov committed 1 year ago

Verified 00c24acb

CANN: Add Ascend CANN build ci (#10217)

xuedinge233 committed 1 year ago

Verified 466ea66f

hip : Add hipGraph and VMM support to ROCM (#11362)

IMbackK committed 1 year ago

Verified 5f0db952

CUDA: fix FP16 cuBLAS GEMM (#11396)

JohannesGaessler committed 1 year ago

Verified c5d9effb

rocBLAS: Avoid fp32->fp16->fp32 conversion on cdna (#11356)

IMbackK committed 1 year ago

Verified 9fbadaef

release : pack /lib in the packages (#11392)

ggerganov committed 1 year ago

Verified 9755129c

docs : Update readme to build targets for local docker build (#11368)

JafarAbdi committed 1 year ago

Verified a07c2c8a

CPU/CUDA: fix (GQA) mul mat back, add CUDA support (#11380)

JohannesGaessler committed 1 year ago

Verified 8137b4bb

cmake : avoid -march=native when reproducible build is wanted (#11366)

Bernhard M. Wiedemann committed 1 year ago

Verified 1af6945e

Update llama-run README.md (#11386)

ericcurtin committed 1 year ago

Verified 01f37edf

server : (webui) put DeepSeek R1 CoT in a collapsible <details> element (#11364)

stduhpf committed 1 year ago

Verified c07e87f3

tests: fix some mul_mat test gaps (#11375)

jeffbolznv committed 1 year ago

Verified 564804b7

Update documentation (#11373)

ericcurtin committed 1 year ago

Verified 05f63cc9

Add -ngl (#11372)

ericcurtin committed 1 year ago

Verified f7fb43cd

server : add more clean up when cancel_tasks is called (#11340)

ngxson committed 1 year ago

Verified 58456616

Treat hf.co/ prefix the same as hf:// (#11350)

ericcurtin committed 1 year ago

Verified f211d1dc

Vulkan-run-test: fix mmq_wg_denoms (#11343)

AMD-dwang committed 1 year ago

Verified 955a6c2d

vulkan: sort shaders for more deterministic binary (#11315)

jeffbolznv committed 1 year ago

Verified 1971adf5

vulkan: fix diag_mask_inf (#11323)

jeffbolznv committed 1 year ago

Verified 5245729e

main : update README documentation for batch size (#11353)

slaren committed 1 year ago

Verified 6152129d

readme : add plugin links (#11355)

ggerganov committed 1 year ago

Verified 16d3df7a

server : fix draft context not being released (#11354)

slaren committed 1 year ago

Verified 12c2bdf2

`minja`: sync at https://github.com/google/minja/commit/0f5f7f2b3770eb682fbc11763266d45204173686 (#11352)

ochafik committed 1 year ago

Verified c64d2bec

Newer Older