 le.chang
|
cbbd1efa06
Makefile: use variables for cublas (#5689)
|
1 year ago |
 Xuan Son Nguyen
|
b11a93df41
fix server hangs on empty prompt (#5733)
|
1 year ago |
 Kawrakow
|
a33e6a0d2a
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)
|
1 year ago |
 Johannes Gäßler
|
47bb7b48c7
CUDA: fix DEBUG_CUDA_MALLOC (#5729)
|
1 year ago |
 Artem
|
c4d7f81786
readme : update ui list (#5731)
|
1 year ago |
 AidanBeltonS
|
e849078c6e
[SYCL] Add support for soft_max ALiBi (#5639)
|
1 year ago |
 Georgi Gerganov
|
67fd33132f
unicode : reuse iterator (#5726)
|
1 year ago |
 Pierrick Hymbert
|
4804215cb8
server: CI fix trailing space (#5728)
|
1 year ago |
|
Pierrick Hymbert
|
8a533f0d90
server: CI tests reduce build matrix (#5725)
|
1 year ago |
|
Georgi Gerganov
|
269de86ba0
llama : fix Gemma rope type (#5691)
|
1 year ago |
 github-actions[bot]
|
c393733988
flake.lock: Update
|
1 year ago |
|
Pierrick Hymbert
|
e3965cf35a
server: tests - slow inference causes timeout on the CI (#5715)
|
1 year ago |
|
Pierrick Hymbert
|
8b350356b2
server: docs - refresh and tease a little bit more the http server (#5718)
|
1 year ago |
|
Georgi Gerganov
|
bf08e00643
llama : refactor k-shift implementation + KV defragmentation (#5691)
|
1 year ago |
 compilade
|
f7625019c5
server : fix crash when system prompt is bigger than batch size (#5714)
|
1 year ago |
 Radosław Gryta
|
abbabc5e51
ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (#5711)
|
1 year ago |
 kwin1412
|
f1a98c5254
make : fix nvcc version is empty (#5713)
|
1 year ago |
 Ashok Gelal
|
7d548a1827
readme : add Msty to UI list (#5618)
|
1 year ago |
|
Pierrick Hymbert
|
930b178026
server: logs - unified format and --log-format option (#5700)
|
1 year ago |
|
Pierrick Hymbert
|
d52d7819b8
server: concurrency fix + monitoring - add /metrics prometheus compatible endpoint (#5708)
|
1 year ago |
|
Radosław Gryta
|
1289408817
cmake : fix compilation for Android armeabi-v7a (#5702)
|
1 year ago |
|
Georgi Gerganov
|
ab336a9d5e
code : normalize enum names (#5697)
|
1 year ago |
 Anas Ahouzi
|
69917dfa55
py : fix StableLM conversion after config.json changes (#5703)
|
1 year ago |
|
Pierrick Hymbert
|
9e359a4f47
server: continue to update other slots on embedding concurrent request (#5699)
|
1 year ago |
|
Kawrakow
|
4c4cb30736
IQ3_S: a much better alternative to Q3_K (#5676)
|
1 year ago |
|
Pierrick Hymbert
|
525213d2f5
server: init functional tests (#5566)
|
1 year ago |
 AlpinDale
|
fd43d66f46
server : add KV cache quantization options (#5684)
|
1 year ago |
 Jared Van Bortel
|
54fbcd2ce6
convert : fix missing ftype for gemma (#5690)
|
1 year ago |
|
Jared Van Bortel
|
15499eb942
mpt : do not duplicate token_embd.weight on disk (#5670)
|
1 year ago |
|
Georgi Gerganov
|
96633eeca1
gemma : use more bits for the token_embd.weight tensor (#5650)
|
1 year ago |
