 slaren
|
1b2f992cd2
test-backend-ops : use flops for some performance tests (#9657)
|
1 год назад |
 Georgi Gerganov
|
739842703e
llama : add comment about thread-safety [no ci] (#9449)
|
1 год назад |
 Zhenwei Jin
|
6102037bbb
vocab : refactor tokenizer to reduce init overhead (#9449)
|
1 год назад |
 nopperl
|
9a913110cf
llama : add support for Chameleon (#8543)
|
1 год назад |
 Aarni Koskela
|
43bcdd9703
readme : add tool (#9655)
|
1 год назад |
 Dan Johansson
|
6a0f779484
ggml : add run-time detection of neon, i8mm and sve (#9331)
|
1 год назад |
 Markus Tavenrath
|
89f9944981
Enable use to the rebar feature to upload buffers to the device. (#9251)
|
1 год назад |
|
Georgi Gerganov
|
b5de3b74a5
readme : update hot topics
|
1 год назад |
 Borislav Stanimirov
|
44f59b4301
cmake : add option for common library (#9661)
|
1 год назад |
 Neo Zhang Jianyu
|
95bc82fbc0
[SYCL] add missed dll file in package (#9577)
|
1 год назад |
 R0CKSTAR
|
7691654c68
mtgpu: enable VMM (#9597)
|
1 год назад |
 Xuan Son Nguyen
|
ea9c32be71
ci : fix docker build number and tag name (#9638)
|
1 год назад |
 Charles Xu
|
1e43630218
ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels (#9217)
|
1 год назад |
|
Xuan Son Nguyen
|
afbbfaa537
server : add more env vars, improve gen-docs (#9635)
|
1 год назад |
 Gabe Goodhart
|
3d6bf6919f
llama : add IBM Granite MoE architecture (#9438)
|
1 год назад |
 Dou Xinpeng
|
904837e0cb
cann: fix crash when llama-bench is running on multiple cann devices (#9627)
|
1 год назад |
 Eric Zhang
|
70392f1f81
ggml : add AVX512DQ requirement for AVX512 builds (#9622)
|
1 год назад |
|
Georgi Gerganov
|
bb5f819975
sync : ggml
|
1 год назад |
|
Georgi Gerganov
|
c038931615
examples : adapt to ggml.h changes (ggml/0)
|
1 год назад |
|
Georgi Gerganov
|
31ac5834fe
llama : keep track of all EOG tokens in the vocab (#9609)
|
1 год назад |
|
Georgi Gerganov
|
cea1486ecf
log : add CONT level for continuing previous log entry (#9610)
|
1 год назад |
 StrangeBytesDev
|
0aa15011e3
server : add newline after chat example (#9616)
|
1 год назад |
|
Georgi Gerganov
|
b0f27361f3
sampling : avoid expensive softmax during greedy sampling (#9605)
|
1 год назад |
 Max Krasnyansky
|
c087b6f11d
threads: fix msvc build without openmp (#9615)
|
1 год назад |
 Ivan
|
116efee0ee
cuda: add q8_0->f32 cpy operation (#9571)
|
1 год назад |
|
Xuan Son Nguyen
|
0b3bf966f4
server : add --no-context-shift option (#9607)
|
1 год назад |
|
Max Krasnyansky
|
f0c7b5edf8
threads: improve ggml_barrier scaling with large number of threads (#9598)
|
1 год назад |
 Riceball LEE
|
1d48e98e4f
readme : add programmable prompt engine language CLI (#9599)
|
1 год назад |
|
Georgi Gerganov
|
f3979df762
flake.lock: Update (#9586)
|
1 год назад |
 Srihari-mcw
|
1e7b9299c6
ggml : AVX512 gemm for Q4_0_8_8 (#9532)
|
1 год назад |
