 Daniel Bevenius
|
a2df2787b3
server : update help metrics processing/deferred (#11512)
|
11 ヶ月 前 |
 Olivier Chafik
|
553f1e46e9
`ci`: ccache for all github worfklows (#11516)
|
11 ヶ月 前 |
|
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
11 ヶ月 前 |
 uvos
|
27d135c970
HIP: require at least HIP 5.5
|
11 ヶ月 前 |
|
uvos
|
6af1ca48cb
HIP: Prepare reduction operators for wave 64
|
11 ヶ月 前 |
|
uvos
|
c300e68ef4
CUDA/HIP: add warp_size to cuda_device_info
|
11 ヶ月 前 |
|
Olivier Chafik
|
3d804dec76
sync: minja (#11499)
|
11 ヶ月 前 |
 mgroeber9110
|
ffd0821c57
vocab : correctly identify LF token for GPT-2 style BPE tokenizer (#11496)
|
11 ヶ月 前 |
|
Daniel Bevenius
|
4314e56c4f
server : use lambda instead of std::bind (#11507)
|
11 ヶ月 前 |
 Isaac McFadyen
|
496e5bf46b
server : (docs) added response format for /apply-template [no ci] (#11503)
|
11 ヶ月 前 |
 Guspan Tanadi
|
7919256c57
readme : reference examples relative links (#11505)
|
11 ヶ月 前 |
|
Daniel Bevenius
|
e0449763a4
server : update json snippets in README.md [no ci] (#11492)
|
11 ヶ月 前 |
 Nigel Bosch
|
eb7cf15a80
server : add /apply-template endpoint for additional use cases of Minja functionality (#11489)
|
11 ヶ月 前 |
 Rémy Oudompheng
|
66ee4f297c
vulkan: implement initial support for IQ2 and IQ3 quantizations (#11360)
|
11 ヶ月 前 |
|
Daniel Bevenius
|
e51c47b401
server : update auto gen files comments [no ci] (#11484)
|
11 ヶ月 前 |
 Jeff Bolz
|
2711d0215f
vulkan: Catch pipeline creation failure and print an error message (#11436)
|
11 ヶ月 前 |
 Eric Curtin
|
f0d4b29edf
Parse https://ollama.com/library/ syntax (#11480)
|
11 ヶ月 前 |
 Georgi Gerganov
|
815857791d
sync : ggml
|
11 ヶ月 前 |
 William Tambellini
|
1a0e87d291
ggml : add option to not print stack on abort (ggml/1081)
|
1 年間 前 |
 issixx
|
d2e518e9b4
ggml-cpu : fix ggml_graph_compute_thread did not terminate on abort. (ggml/1065)
|
1 年間 前 |
|
Daniel Bevenius
|
b636228c0a
embedding : enable --no-warmup option (#11475)
|
11 ヶ月 前 |
 Molly Sophia
|
325afb370a
llama: fix missing k_cache store for rwkv6qwen2 (#11445)
|
11 ヶ月 前 |
 Emreerdog
|
794fe23f29
cmake: add hints for locating ggml on Windows using Llama find-package (#11466)
|
11 ヶ月 前 |
 peidaqi
|
cf8cc856d7
server : Fixed wrong function name in llamacpp server unit test (#11473)
|
11 ヶ月 前 |
 Xuan-Son Nguyen
|
d0c08040b6
ci : fix build CPU arm64 (#11472)
|
11 ヶ月 前 |
 uvos
|
be5ef7963f
HIP: Supress transformation warning in softmax.cu
|
11 ヶ月 前 |
 Nikita Sarychev
|
cae9fb4361
HIP: Only call rocblas_initialize on rocblas versions with the multiple instantation bug (#11080)
|
11 ヶ月 前 |
|
Eric Curtin
|
7fee2889e6
Add github protocol pulling and http:// (#11465)
|
11 ヶ月 前 |
 Nuno
|
d7d1eccacc
docker: allow installing pip packages system-wide (#11437)
|
11 ヶ月 前 |
 someone13574
|
4bf3119d61
cmake : don't fail on `GGML_CPU=OFF` (#11457)
|
11 ヶ月 前 |
