 Acly
|
638d330246
ggml : fix graph reallocation with multiple chunks (#16396)
|
hai 3 meses |
 Aleksander Grygier
|
84c8e305e8
Fix missing messages on sibling navigation (#16408)
|
hai 3 meses |
 Jeff Bolz
|
2aaf0a2a20
vulkan: Replace uses of maxMemoryAllocationSize and VK_WHOLE_SIZE (#16354)
|
hai 3 meses |
|
Jeff Bolz
|
0e1f838556
vulkan: Fix FA coopmat1 invalid array indexing (#16365)
|
hai 3 meses |
 Daniel Bevenius
|
ad126479c2
ci : change macos-13 to macos-15-intel (#16401)
|
hai 3 meses |
|
Aleksander Grygier
|
77233277c9
Capture model name only after first token (streaming) or completed request (#16405)
|
hai 3 meses |
|
Jeff Bolz
|
e308efda8e
vulkan: in flash attention, bounds check against nem1 (don't rely on GGML_KQ_MASK_PAD) (#16316)
|
hai 3 meses |
|
Aleksander Grygier
|
136bda78c5
webui : Fix messages payload sent to chat completions (#16402)
|
hai 3 meses |
 Pascal
|
5113efd34c
fix: track viewportHeight via window.innerHeight to avoid unwanted scrolling (#16356)
|
hai 3 meses |
 Sigbjørn Skjæret
|
d64c8104f0
test-barrier : do not use more threads than physically available (#16389)
|
hai 3 meses |
 Reese Levine
|
ef07a40906
ggml webgpu: add support for soft_max, optimize rms_norm (#16357)
|
hai 3 meses |
 Piotr Wilkin (ilintar)
|
34fcc5a4ac
model : Apertus model implementation (#15852)
|
hai 3 meses |
 R0CKSTAR
|
91a2a56556
musa: update compile flags (#16265)
|
hai 3 meses |
|
Sigbjørn Skjæret
|
72ee736c44
ci : fix ubuntu-latest-cmake-rpc (disable ccache) (#16388)
|
hai 3 meses |
 Eve
|
f09aefaa84
ci: update vulkan ci (#16294)
|
hai 3 meses |
 Georgi Gerganov
|
bbd32bc038
ci : fix clean-up of old logs (#16381)
|
hai 3 meses |
 Neo Zhang Jianyu
|
2be72c2b12
SYCL: Update to oneAPI 2025.2 (#16371)
|
hai 3 meses |
 uvos
|
95ce098544
HIP: add IMbackK to codeowner (#16375)
|
hai 3 meses |
|
uvos
|
c8dedc9999
CI: reenable cdna in rocm docker builds (#16376)
|
hai 3 meses |
|
uvos
|
e95fec640f
HIP: Disable ROCWMMA fattn on CDNA when compiled against ROCWMMA 2.0.0 (#16221)
|
hai 3 meses |
 Shunta Saito
|
ded67b9444
llama : parameter conversion and loading fixes for PLaMo2 variants (#16075)
|
hai 3 meses |
|
uvos
|
1fe4e38cc2
ci: Properly install rocwmma for hip builds (#16305)
|
hai 3 meses |
 Adrien Gallouët
|
4201deae9c
common: introduce http.h for httplib-based client (#16373)
|
hai 3 meses |
|
Aleksander Grygier
|
764799279f
Conversation action dialogs as singletons from Chat Sidebar + apply conditional rendering for Actions Dropdown for Chat Conversation Items (#16369)
|
hai 3 meses |
|
Aleksander Grygier
|
2a9b63383a
Improve code block color theming (#16325)
|
hai 3 meses |
|
Sigbjørn Skjæret
|
1104ca1a1c
ci : use registry cache for docker builds (#16366)
|
hai 3 meses |
|
Aleksander Grygier
|
4f1575921c
Add optional setting for showing "Model used:" information (#16337)
|
hai 3 meses |
|
Eve
|
132d673554
vulkan: make ggml_vk_default_dispatcher support older vulkan headers (#16345)
|
hai 3 meses |
|
Aleksander Grygier
|
aa9538a63a
webui: Remove running `llama-server` within WebUI `dev.sh` script (#16363)
|
hai 3 meses |
 Bartowski
|
e74c92e842
model : support GLM 4.6 (make a few NextN/MTP tensors not required) (#16359)
|
hai 3 meses |
