 Piotr Wilkin (ilintar)
|
746f9ee889
Override SSM_A op for Qwen3 Next to reduce splits (#17587)
|
2 bulan lalu |
 Jeff Bolz
|
9810cb8247
ops.md: update vulkan support (#17661)
|
2 bulan lalu |
 Xuan-Son Nguyen
|
ecf74a8417
mtmd: add mtmd_context_params::warmup option (#17652)
|
2 bulan lalu |
 Gilad S.
|
00c361fe53
fix: llama arch implementation (#17665)
|
2 bulan lalu |
|
Xuan-Son Nguyen
|
ec18edfcba
server: introduce API for serving / loading / unloading multiple models (#17470)
|
2 bulan lalu |
|
Xuan-Son Nguyen
|
7733409734
common: improve verbosity level definitions (#17630)
|
2 bulan lalu |
|
Xuan-Son Nguyen
|
cd3c118908
model: support Ministral3 (#17644)
|
2 bulan lalu |
 Georgi Gerganov
|
649495c9d9
metal : add FA head size 48 (#17619)
|
2 bulan lalu |
|
Georgi Gerganov
|
90c72a614a
ggml : extend the GGML_SCHED_NO_REALLOC debug logic of the scheduler (#17617)
|
2 bulan lalu |
 Aman Gupta
|
6eea666912
llama-graph: avoid expand_forward for fusion (#17633)
|
2 bulan lalu |
|
Xuan-Son Nguyen
|
ff90508d68
contributing: update guidelines for AI-generated code (#17625)
|
2 bulan lalu |
 Adrien Gallouët
|
0a4aeb927d
cmake : add option to build and link LibreSSL (#17552)
|
2 bulan lalu |
 Tarek Dakhran
|
2ba719519d
model: LFM2-VL fixes (#17577)
|
2 bulan lalu |
|
Xuan-Son Nguyen
|
7f8ef50cce
clip: fix nb calculation for qwen3-vl (#17594)
|
2 bulan lalu |
|
Xuan-Son Nguyen
|
3c136b21a3
cli: add migration warning (#17620)
|
2 bulan lalu |
|
Adrien Gallouët
|
beb1f0c503
common : throttle download progress output to reduce IO flush (#17427)
|
2 bulan lalu |
 Aaron Teo
|
def5404f26
common: add LLAMA_LOG_FILE env var (#17609)
|
2 bulan lalu |
|
Gilad S.
|
fa0465954f
ggml: fix: macOS build with `-DGGML_BACKEND_DL=ON` (#17581)
|
2 bulan lalu |
 ddh0
|
5a6241feb0
common: update env var name (#17588)
|
2 bulan lalu |
|
Aman Gupta
|
c7af376c29
CUDA: add stream-based concurrency (#16991)
|
2 bulan lalu |
 Mahekk Shaikh
|
00425e2ed1
cuda : add error checking for cudaMemcpyAsync in argsort (#17599)
|
2 bulan lalu |
 Acly
|
385c3da5e6
vulkan : fix FA mask load with bounds check (coopmat2) (#17606)
|
2 bulan lalu |
|
Xuan-Son Nguyen
|
ab49f094d2
server: move server-context to its own cpp|h (#17595)
|
2 bulan lalu |
 Haiyue Wang
|
8c32d9d96d
server: explicitly set the function name in lambda (#17538)
|
2 bulan lalu |
 Igor Smirnov
|
0874693b44
common : fix json schema with '\' in literals (#17307)
|
2 bulan lalu |
 Neo Zhang
|
7d2add51d8
sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566)
|
2 bulan lalu |
 ixgbe
|
f698a79c63
ggml: replace hwcap with riscv_hwprobe for RVV detection (#17567)
|
2 bulan lalu |
 Ruben Ortlam
|
47a268ea50
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (#16900)
|
2 bulan lalu |
|
Jeff Bolz
|
59d8d4e963
vulkan: improve topk perf for large k, fix overflow in unit tests (#17582)
|
2 bulan lalu |
 Aleksei Nikiforov
|
d82b7a7c1d
gguf-py : fix passing non-native endian tensors (editor-gui and new-metadata) (#17553)
|
2 bulan lalu |
