 Jeff Bolz
|
0c74b04376
vulkan: fix NaN issue in flash attention shader (#12776)
|
9 months ago |
|
Jeff Bolz
|
80b717d493
vulkan: Use unclamped loads for flash attention mask (#12720)
|
9 months ago |
 0cc4m
|
6bf28f0111
Vulkan: Tune Vulkan mmq int dot shader for performance (#12767)
|
9 months ago |
 Sergey Fedorov
|
f1e3eb4249
common : fix includes in arg.cpp and gemma3-cli.cpp (#12766)
|
9 months ago |
 Xuan-Son Nguyen
|
0364178ca2
clip : refactor clip_init, add tests (#12757)
|
9 months ago |
 エシュナヴァリシア
|
c6ff5d2a8d
common: custom hf endpoint support (#12769)
|
9 months ago |
 Olivier Chafik
|
7a84777f42
sync: minja (#12739)
|
9 months ago |
 Georgi Gerganov
|
3e1d29348b
kv-cache : simplify + fix warning for recurrent models (#12756)
|
9 months ago |
 bandoti
|
1be76e4620
ci: add Linux cross-compile build (#12428)
|
9 months ago |
 Nauful Shaikh
|
b772394297
server : webui : Upgrade daisyui, tailwindcss. (#12735)
|
9 months ago |
 nick huang
|
23106f94ea
gguf-split : --merge now respects --dry-run option (#12681)
|
9 months ago |
 Nicolò Scipione
|
94148ba330
sycl: allow ggml-sycl configuration and compilation using Visual Studio project/solution (#12625)
|
9 months ago |
 Ronny Brendel
|
9ac4d611d0
cmake: fix ggml-shaders-gen compiler paths containing spaces (#12747)
|
9 months ago |
 Daniel Bevenius
|
348888e0dc
docs : add XCFramework section to README.md [no ci] (#12746)
|
9 months ago |
|
Jeff Bolz
|
74d4f5b041
vulkan: Hybrid waitForFences/getFenceStatus to reduce fence latency (#12630)
|
9 months ago |
|
Jeff Bolz
|
35e592eb30
vulkan: set cmake minimum and project name in vulkan-shaders (#12744)
|
9 months ago |
 lhez
|
7d7b1bafa7
opencl: update doc for OpenCL (#12702)
|
9 months ago |
 Gaurav Garg
|
c262beddf2
CUDA: Prefer vector flash decoding kernel for Gemma models (#12738)
|
9 months ago |
 yumeyao
|
5dd5d1ab00
vocab : use string_view::find() to avoid unnecessary looking up beyond the fragment range (#12706)
|
9 months ago |
|
Jeff Bolz
|
1c059995e0
vulkan: Fix missing cmake logic for dot product extension (#12721)
|
9 months ago |
 Atharva Dubey
|
2004644b7a
ci : add env variable in ggml-ci and document the same in SYCL.md (#12736)
|
9 months ago |
 R0CKSTAR
|
5f696e88e0
sync : minja (inclusionAI/Ling) and update tests (#12699)
|
9 months ago |
 a3sh
|
193c3e03a6
fix MUSA compiler warning (#12704)
|
9 months ago |
 Chenguang Li
|
65cfe136a0
CANN: Support operator SIN COS ARGMAX (#12709)
|
9 months ago |
 Alan Gray
|
3f9da22c2b
Simplify and improve CUDA graphs through use of indirect copy pointers (#9017)
|
9 months ago |
 hipudding
|
2a0dc97e56
CANN: Fix failed test cases (#12708)
|
9 months ago |
|
lhez
|
97a20c012b
opencl: use `max_alloc_size` in backend ctx instead of querying again (#12705)
|
9 months ago |
|
Jeff Bolz
|
f01bd02376
vulkan: Implement split_k for coopmat2 flash attention. (#12627)
|
9 months ago |
|
bandoti
|
6f3bd38640
cmake: remove caching from vulkan coopmat checks (#12719)
|
9 months ago |
|
Jeff Bolz
|
be0a0f8cae
vulkan: Implement grouped query attention in the coopmat2 FA shader (#12559)
|
9 months ago |
