 Diego Devesa
|
32d6ee6385
ggml : fix const usage in SSE path (#10962)
|
1 anno fa |
 Xuan Son Nguyen
|
14b699ecde
server : fix missing model id in /model endpoint (#10957)
|
1 anno fa |
|
Xuan Son Nguyen
|
485dc01214
server : add system_fingerprint to chat/completion (#10917)
|
1 anno fa |
 Radoslav Gerganov
|
86bf31cfe6
rpc-server : add support for the SYCL backend (#10934)
|
1 anno fa |
 Yun Dou
|
b92a14a841
llama : support InfiniAI Megrez 3b (#10893)
|
1 anno fa |
 ymcki
|
6f0c9e034b
llama : support for Llama-3_1-Nemotron-51B (#10669)
|
1 anno fa |
 Eric Curtin
|
dab76c92cc
llama-run : include temperature option (#10899)
|
1 anno fa |
 yuri@FreeBSD
|
7024d59e6a
ggml : fix run-time on FreeBSD in get_executable_path() (#10948)
|
1 anno fa |
 Rudi Servo
|
7c0e285858
devops : add docker-multi-stage builds (#10832)
|
1 anno fa |
 Billel Mokeddem
|
7ae33a616f
llama : add Falcon3 support (#10883)
|
1 anno fa |
 Jeff Bolz
|
ebdee9478c
vulkan: build fixes for 32b (#10927)
|
1 anno fa |
 Georgi Gerganov
|
5cd85b5e00
convert : add BertForMaskedLM (#10919)
|
1 anno fa |
|
Jeff Bolz
|
a91a41364b
vulkan: optimize coopmat2 dequant functions (#10855)
|
1 anno fa |
 Adrien Gallouët
|
e34c5af43f
ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0() (#10874)
|
1 anno fa |
 Akarshan Biswas
|
eb5c3dc64b
SYCL: Migrate away from deprecated ggml_tensor->backend (#10840)
|
1 anno fa |
|
Xuan Son Nguyen
|
0ca416c91a
server : (UI) fix copy to clipboard function (#10916)
|
1 anno fa |
|
Diego Devesa
|
21ae3b9be8
ggml : add test for SVE and disable when it fails (#10906)
|
1 anno fa |
 Molly Sophia
|
0a11f8b7b5
convert : fix RWKV v6 model conversion (#10913)
|
1 anno fa |
|
Georgi Gerganov
|
d408bb9268
clip : disable GPU support (#10896)
|
1 anno fa |
|
Georgi Gerganov
|
5cab3e4aaa
llama : minor grammar refactor (#10897)
|
1 anno fa |
|
Georgi Gerganov
|
36319dec5d
tts : small QoL for easy model fetch (#10903)
|
1 anno fa |
|
Xuan Son Nguyen
|
57bb2c40cd
server : fix logprobs, make it OAI-compatible (#10783)
|
1 anno fa |
|
Adrien Gallouët
|
a3c33b1dce
ggml: fix arm build with gcc (#10895)
|
1 anno fa |
 Sukriti Sharma
|
2fffc52b50
llama : fix Roberta embeddings (#10856)
|
1 anno fa |
 fairydreaming
|
7585edbdeb
convert : Add support for Microsoft Phi-4 model (#10817)
|
1 anno fa |
 Johannes Gäßler
|
cd920d0ac3
tests: disable GGUF test for bad value size (#10886)
|
1 anno fa |
|
Eric Curtin
|
7909e8588d
llama-run : improve progress bar (#10821)
|
1 anno fa |
|
Diego Devesa
|
9177484f58
ggml : fix arm build (#10890)
|
1 anno fa |
|
Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 anno fa |
 Gaetan Bisson
|
7bbb5acf12
server: avoid overwriting Authorization header (#10878)
|
1 anno fa |
