 codezjx
|
3edfa7d375
llama.android: add field formatChat to control whether to parse special tokens when send message (#11270)
|
пре 1 година |
 Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
пре 1 година |
 Georgi Gerganov
|
a133566d34
vocab : fix double-eos check (#11273)
|
пре 1 година |
 David Renshaw
|
960ec65273
llama : fix deprecation message: vocabable -> vocab (#11269)
|
пре 1 година |
 musoles
|
7a689c415e
README : added kalavai to infrastructure list (#11216)
|
пре 1 година |
 Jeff Bolz
|
bd38ddea01
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (#11166)
|
пре 1 година |
|
Jeff Bolz
|
466300fe14
vulkan: optimize coopmat2 q4_k/q5_k dequant functions. (#11206)
|
пре 1 година |
|
Jeff Bolz
|
206bc53422
vulkan: optimize coopmat2 q2_k dequant function (#11130)
|
пре 1 година |
 RunningLeon
|
4dbc8b9cb7
llama : add internlm3 support (#11233)
|
пре 1 година |
 Johannes Gäßler
|
9c8dcefe17
CUDA: backwards pass for misc. ops, add tests (#11257)
|
пре 1 година |
 Xuan Son Nguyen
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
пре 1 година |
 fj-y-saito
|
c67cc9837d
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (#11227)
|
пре 1 година |
 Eve
|
adc5dd92e8
vulkan: scale caching for k quants + misc fixes (#11081)
|
пре 1 година |
|
Georgi Gerganov
|
f11cfdfd7f
ci : use -no-cnv in gguf-split tests (#11254)
|
пре 1 година |
 Junil Kim
|
1d8504338e
fix: ggml: fix vulkan-shaders-gen build (#10448)
|
пре 1 година |
|
Johannes Gäßler
|
432df2d5f9
RoPE: fix back, CUDA support for back + noncont. (#11240)
|
пре 1 година |
 Daniel Bevenius
|
0ccd7f3eb2
examples : add embd_to_audio to tts-outetts.py [no ci] (#11235)
|
пре 1 година |
 Akarshan Biswas
|
f446c2cf6a
SYCL: Add gated linear attention kernel (#11175)
|
пре 1 година |
|
Xuan Son Nguyen
|
b4d92a59a2
ci : add -no-cnv for tests (#11238)
|
пре 1 година |
|
Georgi Gerganov
|
bbf3e55e35
vocab : add dummy tokens for "no_vocab" type (#11231)
|
пре 1 година |
 ebraminio
|
c5bf0d1bd7
server : Improve code snippets direction between RTL text (#11221)
|
пре 1 година |
 Olivier Chafik
|
091592d758
Refactor test-chat-template.cpp (#11224)
|
пре 1 година |
|
Georgi Gerganov
|
44d1e796d0
sync : ggml
|
пре 1 година |
|
Georgi Gerganov
|
a4f3f5d8e6
scripts : sync gguf (cont)
|
пре 1 година |
|
Georgi Gerganov
|
48e1ae0e61
scripts : sync gguf
|
пре 1 година |
|
Georgi Gerganov
|
d00a80e89d
scripts : sync opencl
|
пре 1 година |
|
ebraminio
|
504af20ee4
server : (UI) Improve messages bubble shape in RTL (#11220)
|
пре 1 година |
|
Xuan Son Nguyen
|
84a44815f7
cli : auto activate conversation mode if chat template is available (#11214)
|
пре 1 година |
 Andreas Kieslinger
|
39509fb082
cuda : CUDA Graph Compute Function Refactor (precursor for performance improvements) (#11042)
|
пре 1 година |
|
Georgi Gerganov
|
a29f0870d4
contrib : add naming guidelines (cont) (#11177)
|
пре 1 година |
