 Jorge A
|
efc72253f7
server : add "/chat/completions" alias for "/v1/...` (#5722)
|
1 rok temu |
 Kawrakow
|
7c4263d426
ggml : make i-quants work with super-blocks of 64 (CPU,Metal) (#5760)
|
1 rok temu |
|
Kawrakow
|
cb49e0f8c9
Attempt to fix android build (#5752)
|
1 rok temu |
|
Kawrakow
|
0becb22ac0
IQ4_XS: a 4.25 bpw quantization (#5747)
|
1 rok temu |
 Engininja2
|
c24a2a6e60
cuda : replace remaining shfl_xor with calls to warp_reduce functions (#5744)
|
1 rok temu |
|
Engininja2
|
1f30b7a9f1
ggml-quants : fix avx2 iq1_s vec_dot when compiled with gcc (#5742)
|
1 rok temu |
 Georgi Gerganov
|
9d533a77d0
llama : fix defrag bugs + add parameter (#5735)
|
1 rok temu |
 le.chang
|
cbbd1efa06
Makefile: use variables for cublas (#5689)
|
1 rok temu |
 Xuan Son Nguyen
|
b11a93df41
fix server hangs on empty prompt (#5733)
|
1 rok temu |
|
Kawrakow
|
a33e6a0d2a
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)
|
1 rok temu |
 Johannes Gäßler
|
47bb7b48c7
CUDA: fix DEBUG_CUDA_MALLOC (#5729)
|
1 rok temu |
 Artem
|
c4d7f81786
readme : update ui list (#5731)
|
1 rok temu |
 AidanBeltonS
|
e849078c6e
[SYCL] Add support for soft_max ALiBi (#5639)
|
1 rok temu |
|
Georgi Gerganov
|
67fd33132f
unicode : reuse iterator (#5726)
|
1 rok temu |
 Pierrick Hymbert
|
4804215cb8
server: CI fix trailing space (#5728)
|
1 rok temu |
|
Pierrick Hymbert
|
8a533f0d90
server: CI tests reduce build matrix (#5725)
|
1 rok temu |
|
Georgi Gerganov
|
269de86ba0
llama : fix Gemma rope type (#5691)
|
1 rok temu |
 github-actions[bot]
|
c393733988
flake.lock: Update
|
1 rok temu |
|
Pierrick Hymbert
|
e3965cf35a
server: tests - slow inference causes timeout on the CI (#5715)
|
1 rok temu |
|
Pierrick Hymbert
|
8b350356b2
server: docs - refresh and tease a little bit more the http server (#5718)
|
1 rok temu |
|
Georgi Gerganov
|
bf08e00643
llama : refactor k-shift implementation + KV defragmentation (#5691)
|
1 rok temu |
 compilade
|
f7625019c5
server : fix crash when system prompt is bigger than batch size (#5714)
|
1 rok temu |
 Radosław Gryta
|
abbabc5e51
ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (#5711)
|
1 rok temu |
 kwin1412
|
f1a98c5254
make : fix nvcc version is empty (#5713)
|
1 rok temu |
 Ashok Gelal
|
7d548a1827
readme : add Msty to UI list (#5618)
|
1 rok temu |
|
Pierrick Hymbert
|
930b178026
server: logs - unified format and --log-format option (#5700)
|
1 rok temu |
|
Pierrick Hymbert
|
d52d7819b8
server: concurrency fix + monitoring - add /metrics prometheus compatible endpoint (#5708)
|
1 rok temu |
|
Radosław Gryta
|
1289408817
cmake : fix compilation for Android armeabi-v7a (#5702)
|
1 rok temu |
|
Georgi Gerganov
|
ab336a9d5e
code : normalize enum names (#5697)
|
1 rok temu |
 Anas Ahouzi
|
69917dfa55
py : fix StableLM conversion after config.json changes (#5703)
|
1 rok temu |
