 Daniel Bevenius
|
b636228c0a
embedding : enable --no-warmup option (#11475)
|
il y a 1 an |
 Molly Sophia
|
325afb370a
llama: fix missing k_cache store for rwkv6qwen2 (#11445)
|
il y a 1 an |
 Emreerdog
|
794fe23f29
cmake: add hints for locating ggml on Windows using Llama find-package (#11466)
|
il y a 1 an |
 peidaqi
|
cf8cc856d7
server : Fixed wrong function name in llamacpp server unit test (#11473)
|
il y a 1 an |
 Xuan-Son Nguyen
|
d0c08040b6
ci : fix build CPU arm64 (#11472)
|
il y a 1 an |
 uvos
|
be5ef7963f
HIP: Supress transformation warning in softmax.cu
|
il y a 1 an |
 Nikita Sarychev
|
cae9fb4361
HIP: Only call rocblas_initialize on rocblas versions with the multiple instantation bug (#11080)
|
il y a 1 an |
 Eric Curtin
|
7fee2889e6
Add github protocol pulling and http:// (#11465)
|
il y a 1 an |
 Nuno
|
d7d1eccacc
docker: allow installing pip packages system-wide (#11437)
|
il y a 1 an |
 someone13574
|
4bf3119d61
cmake : don't fail on `GGML_CPU=OFF` (#11457)
|
il y a 1 an |
|
Nuno
|
f643120bad
docker: add perplexity and bench commands to full image (#11438)
|
il y a 1 an |
 Akarshan Biswas
|
6e84b0ab8e
SYCL : SOFTMAX F16 mask support and other fixes (#11261)
|
il y a 1 an |
 Michael Engel
|
2b8525d5c8
Handle missing model in CLI parameters for llama-run (#11399)
|
il y a 1 an |
|
Eric Curtin
|
a4417ddda9
Add new hf protocol for ollama (#11449)
|
il y a 1 an |
 Haus1
|
d6d24cd9ed
AMD: parse the architecture as supplied by gcnArchName (#11244)
|
il y a 1 an |
 lexasub
|
a5203b4465
llama : minor fixes for up llama load model speed (#11448)
|
il y a 1 an |
 Johannes Gäßler
|
df984e0147
llama: refactor llama_decode_impl (#11381)
|
il y a 1 an |
 Ihar Hrachyshka
|
acd38efee3
metal: Handle null returned from MTLCreateSystemDefaultDevice() (#11441)
|
il y a 1 an |
|
Xuan Son Nguyen
|
caf773f249
docker : fix ARM build and Vulkan build (#11434)
|
il y a 1 an |
 Georgi Gerganov
|
178a7eb952
metal : use residency sets (#11427)
|
il y a 1 an |
|
Nuno
|
6f53d8a6b4
docker: add missing vulkan library to base layer and update to 24.04 (#11422)
|
il y a 1 an |
 bandoti
|
19f65187cb
cmake: add ggml find package (#11369)
|
il y a 1 an |
 Frank Mai
|
1d8ee06000
rpc: fix register position (#11424)
|
il y a 1 an |
|
Georgi Gerganov
|
2cc9b8c32c
readme : update hot topics
|
il y a 1 an |
 Jeff Bolz
|
f35726c2fb
build: apply MSVC /bigobj option to c/cpp files only (#11423)
|
il y a 1 an |
|
Jeff Bolz
|
4a75d19376
vulkan: compile shaders on-demand (#11406)
|
il y a 1 an |
 uvos
|
26771a1491
Hip: disable VMM on hip as it seams that it dosent work in some configurations (#11420)
|
il y a 1 an |
|
Jeff Bolz
|
ca6baf76c1
build: add /bigobj to MSVC build (#11407)
|
il y a 1 an |
 Diego Devesa
|
6e264a905b
docker : add GGML_CPU_ARM_ARCH arg to select ARM architecture to build for (#11419)
|
il y a 1 an |
|
Xuan Son Nguyen
|
49b0e3cec4
server : fix cleaning up stream task (#11418)
|
il y a 1 an |
