Ruan
|
4f51968aca
readme : update typos (#10863)
|
1 год назад |
Xuan Son Nguyen
|
227d7c5a7f
server : (UI) fix missing async generator on safari (#10857)
|
1 год назад |
Eve
|
7b1ec53f56
vulkan: bugfixes for small subgroup size systems + llvmpipe test (#10809)
|
1 год назад |
Zhiyuan Li
|
160bc039c8
rwkv6: add wkv6 support for Vulkan backend (#10829)
|
1 год назад |
Georgi Gerganov
|
08ea539df2
unicode : improve naming style (#10838)
|
1 год назад |
Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
1 год назад |
Bartowski
|
4ddd199f6f
llava : Allow locally downloaded models for QwenVL (#10833)
|
1 год назад |
Valentin Mamedov
|
a0974156f3
llama : add Deepseek MoE v1 & GigaChat models (#10827)
|
1 год назад |
Georgi Gerganov
|
87cf323cef
scripts : change build path to "build-bench" for compare-commits.sh (#10836)
|
1 год назад |
Vinesh Janarthanan
|
5478bbcd17
server: (UI) add syntax highlighting and latex math rendering (#10808)
|
1 год назад |
Georgi Gerganov
|
b5ae1ddff9
gguf-py : bump to v0.13.0
|
1 год назад |
Michelle Tan
|
89d604f2c8
server: Fix `has_next_line` in JSON response (#10818)
|
1 год назад |
Evgeny Kurnevsky
|
e52aba537a
nix: allow to override rocm gpu targets (#10794)
|
1 год назад |
HimariO
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 год назад |
cduk
|
56eea0781c
Removes spurious \r in output that causes logging in journalctl to treat lines as binary and therefore hidden by default (#10771)
|
1 год назад |
lhez
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
1 год назад |
Eric Curtin
|
c27ac678dd
Opt class for positional argument handling (#10508)
|
1 год назад |
Corentin REGAL
|
11e07fd63b
fix: graceful shutdown for Docker images (#10815)
|
1 год назад |
Jett Janiak
|
4601a8bb67
gguf-py : numpy 2 newbyteorder fix (#9772)
|
1 год назад |
谢乃闻
|
9f35e44592
Fix crash caused by ggml_backend_load_all when launching on Android Activity (#10812)
|
1 год назад |
Eve
|
64ae065511
vulkan: small mul_mat_vec optimizations (#10665)
|
1 год назад |
Akarshan Biswas
|
83ed24a97b
SYCL: Reduce most of the compiler warnings (#10748)
|
1 год назад |
Karol Kontny
|
d583cd03f6
ggml : Fix compilation issues on ARM platform when building without fp16 (#10811)
|
1 год назад |
Xuan Son Nguyen
|
adffa6ffd5
common : improve -ctv -ctk CLI arguments (#10806)
|
1 год назад |
Xuan Son Nguyen
|
274ec65af6
contrib : add ngxson as codeowner (#10804)
|
1 год назад |
a3sh
|
8faa1d4dd4
CUDA: faster non-contiguous concat (#10760)
|
1 год назад |
Diego Devesa
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 год назад |
0cc4m
|
4064c0e3b6
Vulkan: Use improved q4_k and q5_k dequant code in dequant shaders (#10798)
|
1 год назад |
0cc4m
|
dc5301d565
Vulkan: Add VK_EXT_subgroup_size_control support to ensure full subgroups for coopmats (#10721)
|
1 год назад |
Xuan Son Nguyen
|
9fdb124304
common : add missing env var for speculative (#10801)
|
1 год назад |