ggml-org/llama.cpp

Pull Requests Commits

metal : remove stray return

ggerganov committed 1 year ago

Verified d441c31b

ngxson committed 1 year ago

cdb3deae

improve debugging message

ngxson committed 1 year ago

b67a168f

cont : remove obsolete comment [no ci]

ggerganov committed 1 year ago

Verified 29330dcb

clip : print more detailed op support info during warmup

ggerganov committed 1 year ago

Verified bdb43f6e

implement "auto" mode for clip flash attn

ngxson committed 1 year ago

b4955f0a

Merge branch 'master' into gg/clip-fa

ngxson committed 1 year ago

19116a4b

webui: auto-refresh /props on inference start to resync model metadata (#16784)

ServeurpersoCom committed 1 year ago

Verified 2f68ce7c

webui: add HTML/JS preview support to MarkdownContent with sandboxed iframe (#16757)

ServeurpersoCom committed 1 year ago

Verified e4a71599

vendor : update cpp-httplib to 0.27.0 (#16846)

angt committed 1 year ago

Verified dd5e8cab

mtmd: refactor preprocessing + support max/min pixels (#16878)

ngxson committed 1 year ago

Verified cf659bbb

Add a setting to display message generation statistics (#16901)

allozaur committed 1 year ago

Verified d8b860a2

webui: recognize AsciiDoc files as valid text files (#16850)

jhradilek committed 1 year ago

Verified 1ae74882

common : allow --system-prompt-file for diffusion-cli (#16903)

CISC committed 1 year ago

Verified 961660b8

codeowners : update after refactor (#16905)

CISC committed 1 year ago

Verified 74fef412

vulkan: Fix multi_add invalid descriptor usage (#16899)

jeffbolznv committed 1 year ago

Verified 5d8bb900

vulkan: fuse mul_mat+add and mul_mat_id+add_id (#16868)

jeffbolznv committed 1 year ago

Verified 2e76e013

CUDA: Remove unneded bias/gate dims in fused mmvq (#16858)

ORippler committed 1 year ago

Verified d3dc9dd8

refactor : llama-model.cpp (#16252)

pwilkin committed 1 year ago

Verified bea04522

model : Minimax M2 (#16831)

pwilkin committed 1 year ago

Verified 0de0a015

model : add Granite Hybrid nano types (#16896)

giuseppe committed 1 year ago

Verified e58d5856

CUDA: Volta tensor core support for MMF (#16843)

JohannesGaessler committed 1 year ago

Verified 31c511a9

ggerganov committed 1 year ago

6d39015a

CUDA: add expert reduce kernel (#16857)

am17an committed 1 year ago

Verified 4146d6a1

batch : fix consistency checks for the input positions (#16890)

ggerganov committed 1 year ago

Verified 8da3c0e2

server : don't print user inputs to console (#16871)

ggerganov committed 1 year ago

Verified c22473b5

server : fix typos in server.cpp comments [no ci] (#16883)

danbev committed 1 year ago

Verified 0f715b4e

vulkan: disable spirv-opt for rope shaders (#16872)

jeffbolznv committed 1 year ago

Verified d2d931f1

vulkan: Fix crash when FP16 mul_mat accumulation is not supported (#16796)

rillomas committed 1 year ago

Verified 2976b037

vulkan: fix shmem overrun in mmq id shader (#16873)

0cc4m committed 1 year ago

Verified d2a2673d

Older