COMMITS
/ examples/llava/clip.cpp December 4, 2024
P
clip : add sycl support (#10574)
piDack committed
November 29, 2024
T
llava: return false instead of exit (#10546)
Ting Lou committed
November 3, 2024
D
ggml : move CPU backend to a separate file (#10144)
Diego Devesa committed
October 1, 2024
G
metal : reduce command encoding overhead (#9698)
Georgi Gerganov committed
September 15, 2024
G
common : reimplement logging (#9418)
Georgi Gerganov committed
September 12, 2024
G
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)
Georgi Gerganov committed
August 30, 2024
T
llava : the function "clip" should be int (#9237)
tc-mb committed
August 26, 2024
J
llama : fix time complexity of string replacement (#9163)
Justine Tunney committed
August 21, 2024
F
llava : zero-initialize clip_ctx structure fields with aggregate initialization 908)
fairydreaming committed
August 20, 2024
C
llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model. (#8984)
Changyeon Kim committed
August 16, 2024
T
llava : support MiniCPM-V-2.6 (#8967)
tc-mb committed
August 9, 2024
G
llama : better replace_all (cont) (#8926)
Georgi Gerganov committed
T
llava : support MiniCPM-V-2.5 (#7599)
tc-mb committed
July 27, 2024
S
ggml : reduce hash table reset cost (#8698)
slaren committed
July 17, 2024
H
[CANN] Add Ascend NPU backend (#6035)
hipudding committed
June 26, 2024
D
clip : suppress unused variable warnings (#8105)
Daniel Bevenius committed
May 10, 2024
A
llava : fix moondream support (#7163)
Andrei committed
May 8, 2024
G
Revert "llava : add support for moondream vision language model (#6899)"
Georgi Gerganov committed
April 25, 2024
D
clip : rename lerp function to avoid conflict (#6894)
Daniel Bevenius committed
April 21, 2024
J
llava : use logger in llava-cli (#6797)
Justine Tunney committed
March 28, 2024
Z
llava : fix MobileVLM (#6364)
Ziang Wu committed
March 26, 2024
S
cuda : rename build flag to LLAMA_CUDA (#6299)
slaren committed
March 20, 2024
Z
llava : add MobileVLM_V2 backup (#6175)
Ziang Wu committed
G
Revert "llava : add a MobileVLM_V2-1.7B backup (#6152)"
Georgi Gerganov committed
Z
llava : add a MobileVLM_V2-1.7B backup (#6152)
Ziang Wu committed
March 18, 2024
F
clip : fix memory leak (#6138)
Felix committed
March 15, 2024
T
llava : change API to pure C style for Rust FFI bindgen (#6079)
Ting Lou committed
March 14, 2024
S
gguf : fix resource leaks (#6061)
Steve Grubb committed
March 9, 2024
G
ggml : remove old quantization functions (#5942)
Georgi Gerganov committed
February 19, 2024
G
llava : remove extra cont (#5587)
Georgi Gerganov committed
S
llava : replace ggml_cpy with ggml_cont
slaren committed
February 15, 2024
G
clip : fix wrong loop condition
Georgi Gerganov committed
E
llava : fix memory management bug (#5491)
Elbios committed
February 14, 2024
J
llava : support v1.6 (#5267)
John committed
February 12, 2024
G
sync : ggml (#5452)
Georgi Gerganov committed
January 27, 2024
J
llava : support for Yi-VL and fix for mobileVLM (#5093)
John committed
M
Remove unused data and add fixes (#5154)
Michael Klimenko committed
January 23, 2024
G
minor : clean-up some warnings and style (#5094)
Georgi Gerganov committed
January 22, 2024
X
llava : MobileVLM support (#4954)
XiaotaoChen committed
January 10, 2024
J
clip : support more quantization types (#4846)
John committed
December 30, 2023
G
clip : refactor + bug fixes (#4696)
Georgi Gerganov committed
December 29, 2023
G
clip : use ggml_backend_buffer_is_host (#4205)
Georgi Gerganov committed
S
clip : enable gpu backend (#4205)
Steward Garcia committed
December 21, 2023
G
ggml : change ggml_scale to take a float instead of tensor (#4573)
Georgi Gerganov committed
December 14, 2023
S
ggml : remove n_dims from ggml_tensor (#4469)
slaren committed
December 12, 2023
R
english : use `typos` to fix comments and logs (#4354)
Richard Kiss committed
November 13, 2023
M
llava : fix regression for square images in #3613 (#4056)
M. Yusuf Sarıgöz committed
G
sync : ggml (backend v2) (#3912)
Georgi Gerganov committed
November 6, 2023
D
llava : expose as a shared library for downstream projects (#3613)
Damian Stewart committed