 slaren
|
87e397d00b
ggml : fix quant dot product with odd number of blocks (#8549)
|
1 سال پیش |
 Brian
|
57b1d4f9eb
convert-*.py: remove add_name from ChatGLMModel class (#8590)
|
1 سال پیش |
 Georgi Gerganov
|
d197545530
llama : bump max layers from 256 to 512 (#8530)
|
1 سال پیش |
|
Georgi Gerganov
|
be0cfb4175
readme : fix server badge
|
1 سال پیش |
 Clint Herron
|
b57eb9ca4f
ggml : add friendlier error message to fopen errors (#8575)
|
1 سال پیش |
 Frank Mai
|
f299aa98ec
fix: typo of chatglm4 chat tmpl (#8586)
|
1 سال پیش |
|
Brian
|
3d0e4367d9
convert-*.py: add general.name kv override (#8571)
|
1 سال پیش |
 Johannes Gäßler
|
a15ef8f8a0
CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)
|
1 سال پیش |
 65a
|
705b7ecf60
cmake : install all ggml public headers (#8480)
|
1 سال پیش |
 Eric Zhang
|
0d2c7321e9
server: use relative routes for static files in new UI (#8552)
|
1 سال پیش |
|
Brian
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
1 سال پیش |
 RunningLeon
|
3807c3de04
server : respect `--special` cli arg (#8553)
|
1 سال پیش |
|
Johannes Gäßler
|
e02b597be3
lookup: fibonacci hashing, fix crashes (#8548)
|
1 سال پیش |
 Al Mochkin
|
b3283448ce
build : Fix docker build warnings (#8535) (#8537)
|
1 سال پیش |
|
Brian
|
30f80ca0bc
CONTRIBUTING.md : remove mention of noci (#8541)
|
1 سال پیش |
 hipudding
|
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
|
1 سال پیش |
 Masaya, Kato
|
da3913d8f9
batched: fix n_predict parameter (#8527)
|
1 سال پیش |
|
Georgi Gerganov
|
d65a8361fe
llama : disable context-shift for DeepSeek v2 (#8501)
|
1 سال پیش |
|
Johannes Gäßler
|
5e116e8dd5
make/cmake: add missing force MMQ/cuBLAS for HIP (#8515)
|
1 سال پیش |
|
Brian
|
1666f92dcd
gguf-hash : update clib.json to point to original xxhash repo (#8491)
|
1 سال پیش |
 Steve Bonds
|
37b12f92ab
export-lora : handle help argument (#8497)
|
1 سال پیش |
|
Georgi Gerganov
|
0efec57787
llama : valign + remove unused ftype (#8502)
|
1 سال پیش |
 compilade
|
7acfd4e8d5
convert_hf : faster lazy safetensors (#8482)
|
1 سال پیش |
 Xuan Son Nguyen
|
97bdd26eee
Refactor lora adapter support (#8332)
|
1 سال پیش |
|
Xuan Son Nguyen
|
4db8f60fe7
fix ci (#8494)
|
1 سال پیش |
 Daniel Bevenius
|
8fac431b06
ggml : suppress unknown pragma 'GCC' on windows (#8460)
|
1 سال پیش |
 M-A
|
f17f39ff9c
server: update README.md with llama-server --help output [no ci] (#8472)
|
1 سال پیش |
|
Georgi Gerganov
|
9104bc20ed
common : add --no-cont-batching arg (#6358)
|
1 سال پیش |
 NikolaiLyssogor
|
fc690b018e
docs: fix links in development docs [no ci] (#8481)
|
1 سال پیش |
 Meng, Hengyu
|
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
|
1 سال پیش |
