Eve
|
d15d177f43
vulkan: faster q6_k matmul (#17813)
|
1 månad sedan |
Reese Levine
|
7ca5991d2b
ggml webgpu: add support for emscripten builds (#17184)
|
1 månad sedan |
Georgi Gerganov
|
f40a2e5f11
gitignore : be more specific about ignored stuff (#17354)
|
1 månad sedan |
Aleksander Grygier
|
5d0a40f390
Always show message actions for mobile UI + improvements for user message sizing (#16076)
|
3 månader sedan |
Aleksander Grygier
|
a7a98e0fff
SvelteKit-based WebUI (#14839)
|
4 månader sedan |
Copilot
|
245be739df
ci : add copilot-instructions.md (#15286)
|
4 månader sedan |
Xuan-Son Nguyen
|
00fa15fedc
mtmd : add support for Voxtral (#14862)
|
5 månader sedan |
Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
8 månader sedan |
William Tambellini
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 månader sedan |
Xuan-Son Nguyen
|
63ac128563
server : add TEI API format for /rerank endpoint (#11942)
|
11 månader sedan |
Eve
|
adc5dd92e8
vulkan: scale caching for k quants + misc fixes (#11081)
|
1 år sedan |
Xuan Son Nguyen
|
91c36c269b
server : (web ui) Various improvements, now use vite as bundler (#10599)
|
1 år sedan |
Georgi Gerganov
|
20a780c7b6
gitignore : ignore local run scripts [no ci]
|
1 år sedan |
Georgi Gerganov
|
8ee0d09ae6
make : auto-determine dependencies (#0)
|
1 år sedan |
Xuan Son Nguyen
|
1b9ae5189c
common : refactor arg parser (#9308)
|
1 år sedan |
ltoniazzi
|
2339a0be1c
tests : add integration test for lora adapters (#8957)
|
1 år sedan |
tc-mb
|
3071c0a5f2
llava : support MiniCPM-V-2.5 (#7599)
|
1 år sedan |
Austin
|
4730faca61
chore : Fix vulkan related compiler warnings, add help text, improve CLI options (#8477)
|
1 år sedan |
Georgi Gerganov
|
a977c11544
gitignore : deprecated binaries
|
1 år sedan |
Xuan Son Nguyen
|
be20e7f49d
Reorganize documentation pages (#8325)
|
1 år sedan |
ditsuke
|
de14e2ea2b
chore: ignore all __pychache__
|
1 år sedan |
ditsuke
|
b0a46993df
build(python): Package scripts with pip-0517 compliance
|
1 år sedan |
Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 år sedan |
Michael de Gans
|
a7854743c5
un-ignore `build-info.cmake` and `build-info.sh` (#7996)
|
1 år sedan |
Olivier Chafik
|
1c641e6aac
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
|
1 år sedan |
zhouwg
|
b226c1227b
refine .gitignore (#7688)
|
1 år sedan |
Austin
|
7c4e5b7eae
chore : add ignore rule for generated server themes (#7689)
|
1 år sedan |
Olivier Chafik
|
8843a98c2b
Improve usability of --model-url & related flags (#6930)
|
1 år sedan |
Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
1 år sedan |
Olivier Chafik
|
5cf5e7d490
`build`: generate hex dump of server assets during build (#6661)
|
1 år sedan |