 Georgi Gerganov
|
e5edb210cd
server : update deps (#9183)
|
1 年之前 |
 slaren
|
0c41e03ceb
metal : gemma2 flash attention support (#9159)
|
1 年之前 |
|
slaren
|
f12ceaca0c
ggml-ci : try to improve build time (#9160)
|
1 年之前 |
 Justine Tunney
|
436787f170
llama : fix time complexity of string replacement (#9163)
|
1 年之前 |
 Herman Semenov
|
93bc3839f9
common: fixed not working find argument --n-gpu-layers-draft (#9175)
|
1 年之前 |
 Johannes Gäßler
|
f91fc5639b
CUDA: fix Gemma 2 numerical issues for FA (#9166)
|
1 年之前 |
|
Johannes Gäßler
|
e11bd856d5
CPU/CUDA: Gemma 2 FlashAttention support (#8542)
|
1 年之前 |
 João Dinis Ferreira
|
8f824ffe8e
quantize : fix typo in usage help of `quantize.cpp` (#9145)
|
1 年之前 |
 Xuan Son Nguyen
|
3ba780e2a8
lora : fix llama conversion script with ROPE_FREQS (#9117)
|
1 年之前 |
 piDack
|
a07c32ea54
llama : use F32 precision in GLM4 attention and no FA (#9130)
|
1 年之前 |
 Akarshan Biswas
|
11b84eb457
[SYCL] Add a space to supress a cmake warning (#9133)
|
1 年之前 |
 luoyu-intel
|
1731d4238f
[SYCL] Add oneDNN primitive support (#9091)
|
1 年之前 |
 compilade
|
a1631e53f6
llama : simplify Mamba with advanced batch splits (#8526)
|
1 年之前 |
|
Xuan Son Nguyen
|
fc54ef0d1c
server : support reading arguments from environment variables (#9105)
|
1 年之前 |
 Younes Belkada
|
b40eb84895
llama : support for `falcon-mamba` architecture (#9074)
|
1 年之前 |
 fairydreaming
|
f63f603c87
llava : zero-initialize clip_ctx structure fields with aggregate initialization 908)
|
1 年之前 |
 Daniel Bevenius
|
8455340b87
llama : std::move llm_bigram_bpe from work_queue (#9062)
|
1 年之前 |
 Changyeon Kim
|
2f3c1466ff
llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model. (#8984)
|
1 年之前 |
 Meng, Hengyu
|
50addec9a5
[SYCL] fallback mmvq (#9088)
|
1 年之前 |
 zhentaoyu
|
4f8d19ff17
[SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052)
|
1 年之前 |
|
fairydreaming
|
90db8146d5
tests : add missing comma in grammar integration tests (#9099)
|
1 年之前 |
 wangshuai09
|
cfac111e2b
cann: add doc for cann backend (#8867)
|
1 年之前 |
 Radoslav Gerganov
|
1b6ff90ff8
rpc : print error message when failed to connect endpoint (#9042)
|
1 年之前 |
|
Radoslav Gerganov
|
18eaf29f4c
rpc : prevent crashes on invalid input (#9040)
|
1 年之前 |
|
Georgi Gerganov
|
554b049068
flake.lock: Update (#9068)
|
1 年之前 |
 ltoniazzi
|
2339a0be1c
tests : add integration test for lora adapters (#8957)
|
1 年之前 |
 Yoshi Suhara
|
2fb9267887
Fix incorrect use of ctx_split for bias tensors (#9063)
|
1 年之前 |
|
Xuan Son Nguyen
|
8b3befc0e2
server : refactor middleware and /health endpoint (#9056)
|
1 年之前 |
 tc-mb
|
d565bb2fd5
llava : support MiniCPM-V-2.6 (#8967)
|
1 年之前 |
 Farbod Bijary
|
ee2984bdaf
py : fix wrong input type for raw_dtype in ggml to gguf scripts (#8928)
|
1 年之前 |
