 Xuan Son Nguyen
|
97bdd26eee
Refactor lora adapter support (#8332)
|
1 year ago |
|
Xuan Son Nguyen
|
4db8f60fe7
fix ci (#8494)
|
1 year ago |
 Daniel Bevenius
|
8fac431b06
ggml : suppress unknown pragma 'GCC' on windows (#8460)
|
1 year ago |
 M-A
|
f17f39ff9c
server: update README.md with llama-server --help output [no ci] (#8472)
|
1 year ago |
 Georgi Gerganov
|
9104bc20ed
common : add --no-cont-batching arg (#6358)
|
1 year ago |
 NikolaiLyssogor
|
fc690b018e
docs: fix links in development docs [no ci] (#8481)
|
1 year ago |
 Meng, Hengyu
|
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
|
1 year ago |
|
Georgi Gerganov
|
3dfda05956
llama : de-duplicate deepseek2 norm
|
1 year ago |
 0cc4m
|
bda62d7999
Vulkan MMQ Fix (#8479)
|
1 year ago |
 compilade
|
090fca7a07
pydantic : replace uses of __annotations__ with get_type_hints (#8474)
|
1 year ago |
|
Georgi Gerganov
|
aaab2419ea
flake.lock: Update (#8475)
|
1 year ago |
|
Georgi Gerganov
|
73cf442e7b
llama : fix Gemma-2 Query scaling factors (#8473)
|
1 year ago |
 Brian
|
e236528e76
gguf_hash.py: Add sha256 (#8470)
|
1 year ago |
|
compilade
|
fa79495bb4
llama : fix pre-tokenization of non-special added tokens (#8228)
|
1 year ago |
 bandoti
|
17eb6aa8a9
vulkan : cmake integration (#8119)
|
1 year ago |
|
Georgi Gerganov
|
c917b67f06
metal : template-ify some of the kernels (#8447)
|
1 year ago |
|
Georgi Gerganov
|
4e24cffd8c
server : handle content array in chat API (#8449)
|
1 year ago |
|
Georgi Gerganov
|
6af51c0d96
main : print error on empty input (#8456)
|
1 year ago |
|
Daniel Bevenius
|
f53226245f
llama : suppress unary minus operator warning (#8448)
|
1 year ago |
 Douglas Hanley
|
c3ebcfa148
server : ensure batches are either all embed or all completion (#8420)
|
1 year ago |
 Armen Kaleshian
|
8a4441ea1a
docker : fix filename for convert-hf-to-gguf.py in tools.sh (#8441)
|
1 year ago |
 Jiří Podivín
|
5aefbce27a
convert : remove fsep token from GPTRefactForCausalLM (#8237)
|
1 year ago |
|
Georgi Gerganov
|
71c1121d11
examples : sprintf -> snprintf (#8434)
|
1 year ago |
|
Georgi Gerganov
|
370b1f7e7a
ggml : minor naming changes (#8433)
|
1 year ago |
 Chen Xi
|
b549a1bbef
[SYCL] fix the mul_mat_id ut issues (#8427)
|
1 year ago |
 Nicholai Tukanov
|
368645698a
ggml : add NVPL BLAS support (#8329) (#8425)
|
1 year ago |
|
Daniel Bevenius
|
b078c619aa
cuda : suppress 'noreturn' warn in no_device_code (#8414)
|
1 year ago |
 Johannes Gäßler
|
808aba3916
CUDA: optimize and refactor MMQ (#8416)
|
1 year ago |
|
Georgi Gerganov
|
a977c11544
gitignore : deprecated binaries
|
1 year ago |
|
compilade
|
9a55ffe6fb
tokenize : add --no-parse-special option (#8423)
|
1 year ago |
