 Aman Gupta
|
6eea666912
llama-graph: avoid expand_forward for fusion (#17633)
|
1 month ago |
 Xuan-Son Nguyen
|
ff90508d68
contributing: update guidelines for AI-generated code (#17625)
|
1 month ago |
 Adrien Gallouët
|
0a4aeb927d
cmake : add option to build and link LibreSSL (#17552)
|
1 month ago |
 Tarek Dakhran
|
2ba719519d
model: LFM2-VL fixes (#17577)
|
1 month ago |
|
Xuan-Son Nguyen
|
7f8ef50cce
clip: fix nb calculation for qwen3-vl (#17594)
|
1 month ago |
|
Xuan-Son Nguyen
|
3c136b21a3
cli: add migration warning (#17620)
|
1 month ago |
|
Adrien Gallouët
|
beb1f0c503
common : throttle download progress output to reduce IO flush (#17427)
|
1 month ago |
 Aaron Teo
|
def5404f26
common: add LLAMA_LOG_FILE env var (#17609)
|
1 month ago |
 Gilad S.
|
fa0465954f
ggml: fix: macOS build with `-DGGML_BACKEND_DL=ON` (#17581)
|
1 month ago |
 ddh0
|
5a6241feb0
common: update env var name (#17588)
|
1 month ago |
|
Aman Gupta
|
c7af376c29
CUDA: add stream-based concurrency (#16991)
|
1 month ago |
 Mahekk Shaikh
|
00425e2ed1
cuda : add error checking for cudaMemcpyAsync in argsort (#17599)
|
1 month ago |
 Acly
|
385c3da5e6
vulkan : fix FA mask load with bounds check (coopmat2) (#17606)
|
1 month ago |
|
Xuan-Son Nguyen
|
ab49f094d2
server: move server-context to its own cpp|h (#17595)
|
1 month ago |
 Haiyue Wang
|
8c32d9d96d
server: explicitly set the function name in lambda (#17538)
|
1 month ago |
 Igor Smirnov
|
0874693b44
common : fix json schema with '\' in literals (#17307)
|
1 month ago |
 Neo Zhang
|
7d2add51d8
sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566)
|
1 month ago |
 ixgbe
|
f698a79c63
ggml: replace hwcap with riscv_hwprobe for RVV detection (#17567)
|
1 month ago |
 Ruben Ortlam
|
47a268ea50
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (#16900)
|
1 month ago |
 Jeff Bolz
|
59d8d4e963
vulkan: improve topk perf for large k, fix overflow in unit tests (#17582)
|
1 month ago |
 Aleksei Nikiforov
|
d82b7a7c1d
gguf-py : fix passing non-native endian tensors (editor-gui and new-metadata) (#17553)
|
1 month ago |
 DAN™
|
03914c7ef8
common : move all common_chat_parse_* to chat-parser.cpp. (#17481)
|
1 month ago |
 o7si
|
3ce7a65c2f
server: fix: /metrics endpoint returning JSON-escaped Prometheus format (#17386)
|
1 month ago |
 Diego Devesa
|
e072b2052e
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276)
|
1 month ago |
 R0CKSTAR
|
c6f7a423c8
[MUSA] enable fp16/fast_fp16/bf16_mma on PH1 (#17551)
|
1 month ago |
|
Aman Gupta
|
2e7ef98f18
ggml-cuda: add stricter checking for fusion (#17568)
|
1 month ago |
 Fredrik Hultin
|
ddf9f94389
server : add Anthropic Messages API support (#17570)
|
1 month ago |
 Piotr Wilkin (ilintar)
|
ff55414c42
model : Qwen3 Next (#16095)
|
1 month ago |
 Johannes Gäßler
|
73955f7d2a
CUDA: no FP16 arithmetic for vector FA kernel (#17558)
|
1 month ago |
|
Jeff Bolz
|
35cf8887e1
vulkan: Implement GGML_OP_TRI (#17503)
|
1 month ago |
