 Johannes Gäßler
|
e02b597be3
lookup: fibonacci hashing, fix crashes (#8548)
|
1 жил өмнө |
 Al Mochkin
|
b3283448ce
build : Fix docker build warnings (#8535) (#8537)
|
1 жил өмнө |
 Brian
|
30f80ca0bc
CONTRIBUTING.md : remove mention of noci (#8541)
|
1 жил өмнө |
 hipudding
|
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
|
1 жил өмнө |
 Masaya, Kato
|
da3913d8f9
batched: fix n_predict parameter (#8527)
|
1 жил өмнө |
 Georgi Gerganov
|
d65a8361fe
llama : disable context-shift for DeepSeek v2 (#8501)
|
1 жил өмнө |
|
Johannes Gäßler
|
5e116e8dd5
make/cmake: add missing force MMQ/cuBLAS for HIP (#8515)
|
1 жил өмнө |
|
Brian
|
1666f92dcd
gguf-hash : update clib.json to point to original xxhash repo (#8491)
|
1 жил өмнө |
 Steve Bonds
|
37b12f92ab
export-lora : handle help argument (#8497)
|
1 жил өмнө |
|
Georgi Gerganov
|
0efec57787
llama : valign + remove unused ftype (#8502)
|
1 жил өмнө |
 compilade
|
7acfd4e8d5
convert_hf : faster lazy safetensors (#8482)
|
1 жил өмнө |
 Xuan Son Nguyen
|
97bdd26eee
Refactor lora adapter support (#8332)
|
1 жил өмнө |
|
Xuan Son Nguyen
|
4db8f60fe7
fix ci (#8494)
|
1 жил өмнө |
 Daniel Bevenius
|
8fac431b06
ggml : suppress unknown pragma 'GCC' on windows (#8460)
|
1 жил өмнө |
 M-A
|
f17f39ff9c
server: update README.md with llama-server --help output [no ci] (#8472)
|
1 жил өмнө |
|
Georgi Gerganov
|
9104bc20ed
common : add --no-cont-batching arg (#6358)
|
1 жил өмнө |
 NikolaiLyssogor
|
fc690b018e
docs: fix links in development docs [no ci] (#8481)
|
1 жил өмнө |
 Meng, Hengyu
|
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
|
1 жил өмнө |
|
Georgi Gerganov
|
3dfda05956
llama : de-duplicate deepseek2 norm
|
1 жил өмнө |
 0cc4m
|
bda62d7999
Vulkan MMQ Fix (#8479)
|
1 жил өмнө |
|
compilade
|
090fca7a07
pydantic : replace uses of __annotations__ with get_type_hints (#8474)
|
1 жил өмнө |
|
Georgi Gerganov
|
aaab2419ea
flake.lock: Update (#8475)
|
1 жил өмнө |
|
Georgi Gerganov
|
73cf442e7b
llama : fix Gemma-2 Query scaling factors (#8473)
|
1 жил өмнө |
|
Brian
|
e236528e76
gguf_hash.py: Add sha256 (#8470)
|
1 жил өмнө |
|
compilade
|
fa79495bb4
llama : fix pre-tokenization of non-special added tokens (#8228)
|
1 жил өмнө |
 bandoti
|
17eb6aa8a9
vulkan : cmake integration (#8119)
|
1 жил өмнө |
|
Georgi Gerganov
|
c917b67f06
metal : template-ify some of the kernels (#8447)
|
1 жил өмнө |
|
Georgi Gerganov
|
4e24cffd8c
server : handle content array in chat API (#8449)
|
1 жил өмнө |
|
Georgi Gerganov
|
6af51c0d96
main : print error on empty input (#8456)
|
1 жил өмнө |
|
Daniel Bevenius
|
f53226245f
llama : suppress unary minus operator warning (#8448)
|
1 жил өмнө |
