 Georgi Gerganov
|
b69a480af4
readme : refactor API section + remove old hot topics
|
1 rok temu |
 Xuan Son Nguyen
|
48baa61ecc
server : test script : add timeout for all requests (#9282)
|
1 rok temu |
 Zhenwei Jin
|
f1485161e5
src: make tail invalid when kv cell is intersection for mamba (#9249)
|
1 rok temu |
 slaren
|
048de848ee
docker : fix missing binaries in full-cuda image (#9278)
|
1 rok temu |
 yuri@FreeBSD
|
f771d064a9
ggml : add pthread includes on FreeBSD (#9258)
|
1 rok temu |
|
Xuan Son Nguyen
|
6e7d133a5f
server : refactor multitask handling (#9274)
|
1 rok temu |
 Guoliang Hua
|
b60074f1c2
llama-cli : remove duplicated log message (#9275)
|
1 rok temu |
 Tushar
|
9c1ba55733
build(nix): Package gguf-py (#5664)
|
1 rok temu |
|
Georgi Gerganov
|
c6d4cb4655
llama : minor style
|
1 rok temu |
 Molly Sophia
|
8f1d81a0b6
llama : support RWKV v6 models (#8980)
|
1 rok temu |
 Echo Nolan
|
a47667cff4
nix: fix CUDA build - replace deprecated autoAddOpenGLRunpathHook
|
1 rok temu |
 Srihari-mcw
|
ea5d7478b1
sgemm : improved Q4_0 and Q8_0 performance via 4xN and Mx4 gemm (#8908)
|
1 rok temu |
 Daniel Bevenius
|
49271efbaf
llama : fix typo in xcda_array_view comment [no ci] (#9132)
|
1 rok temu |
 Sutou Kouhei
|
0ab30f8d82
llama : fix llama_split_mode enum values in main_gpu document (#9057)
|
1 rok temu |
 蕭澧邦
|
cddae4884c
Correct typo run_llama2.sh > run-llama2.sh (#9149)
|
1 rok temu |
 tc-mb
|
7ea8d80d53
llava : the function "clip" should be int (#9237)
|
1 rok temu |
 Faisal Zaghloul
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 rok temu |
 Jan Boon
|
9f7d4bcf5c
server : fix crash when error handler dumps invalid utf-8 json (#9195)
|
1 rok temu |
|
Georgi Gerganov
|
1d1ccce676
flake.lock: Update (#9162)
|
1 rok temu |
|
slaren
|
9fe94ccac9
docker : build images only once (#9225)
|
1 rok temu |
|
slaren
|
66b039a501
docker : update CUDA images (#9213)
|
1 rok temu |
|
Georgi Gerganov
|
20f1789dfb
vulkan : fix build (#0)
|
1 rok temu |
|
Georgi Gerganov
|
231cff5f6f
sync : ggml
|
1 rok temu |
 Xie Yanbo
|
3246fe84d7
Fix minicpm example directory (#9111)
|
1 rok temu |
 compilade
|
78eb487bb0
llama : fix qs.n_attention_wv for DeepSeek-V2 (#9156)
|
1 rok temu |
|
Xuan Son Nguyen
|
a77feb5d71
server : add some missing env variables (#9116)
|
1 rok temu |
 CausalLM
|
2e59d61c1b
llama : fix ChatGLM4 wrong shape (#9194)
|
1 rok temu |
 Carsten Kragelund Jørgensen
|
75e1dbbaab
llama : fix llama3.1 rope_freqs not respecting custom head_dim (#9141)
|
1 rok temu |
 arch-btw
|
ad76569f8e
common : Update stb_image.h to latest version (#9161)
|
1 rok temu |
|
slaren
|
7d787ed96c
ggml : do not crash when quantizing q4_x_x with an imatrix (#9192)
|
1 rok temu |
