 Georgi Gerganov
|
ecb217db4f
llama : Metal inference (#1642)
|
2 jaren geleden |
 0cc4m
|
dcb2ed4826
OpenCL: Fix duplication of layers in VRAM and RAM, add GPU mul kernel (#1653)
|
2 jaren geleden |
 Henri Vasserman
|
d8bd0013e8
Add info about CUDA_VISIBLE_DEVICES (#1682)
|
2 jaren geleden |
 Jiří Podivín
|
b5c85468a3
Docker: change to calling convert.py (#1641)
|
2 jaren geleden |
 Evan Jones
|
136476e898
Fix prompt cache saving and chat-persistent rollover (#1678)
|
2 jaren geleden |
|
Henri Vasserman
|
ffb06a345e
OpenLLaMA 3B support (#1588)
|
2 jaren geleden |
|
Georgi Gerganov
|
7552ac5863
ggml : sync cgraph import / export API
|
2 jaren geleden |
|
Georgi Gerganov
|
5d1830b99d
ggml : fix bug in ggml_alibi
|
2 jaren geleden |
 DannyDaemonic
|
248367605e
Work around for recalculating logits in cached prompts (Fixes #1585) (#1609)
|
2 jaren geleden |
|
Jiří Podivín
|
0e730dd23b
Adding git in container package dependencies (#1621)
|
2 jaren geleden |
 Johannes Gäßler
|
3b126f654f
LLAMA_DEBUG adds debug symbols (#1617)
|
2 jaren geleden |
 Kerfuffle
|
1b78ed2081
Only show -ngl option when relevant + other doc/arg handling updates (#1625)
|
2 jaren geleden |
 Vladimir Zorin
|
337aea1139
examples : add --alias option to gpt_params to set use friendly model name (#1614)
|
2 jaren geleden |
 Howard Su
|
bb051d9723
opencl : no need to allocate cl_mem on heap (#1612)
|
2 jaren geleden |
|
Howard Su
|
ca74884f66
opencl : use strstr to check if fp16 supported (#1611)
|
2 jaren geleden |
 apcameron
|
a6704643b6
ggml : add support for the RISCV architecture (#1616)
|
2 jaren geleden |
|
Kerfuffle
|
0df7d63e5b
Include server in releases + other build system cleanups (#1610)
|
2 jaren geleden |
|
Henri Vasserman
|
97c9b77c4f
Add documentation about CLBlast (#1604)
|
2 jaren geleden |
|
Henri Vasserman
|
0ecb1bbbeb
[CI] Fix openblas (#1613)
|
2 jaren geleden |
|
Georgi Gerganov
|
93618031c7
ggml : add ggml_tensor_overhead()
|
2 jaren geleden |
|
Henri Vasserman
|
83c54e6da5
[CI] CLBlast: Fix directory name (#1606)
|
2 jaren geleden |
|
Georgi Gerganov
|
bdbda1b17a
ggml : sync ggml core (minor additions, e.g. ggml_get_tensor_by_name())
|
2 jaren geleden |
|
Kerfuffle
|
66874d4fbc
Some improvements to loading the session with --prompt-cache (#1550)
|
2 jaren geleden |
|
Johannes Gäßler
|
1fcdcc28b1
cuda : performance optimizations (#1530)
|
2 jaren geleden |
|
Henri Vasserman
|
ac7876ac20
Update CLBlast to 1.6.0 (#1580)
|
2 jaren geleden |
|
Evan Jones
|
c31bbe934b
readme : add docs for chat-persistent.sh (#1568)
|
2 jaren geleden |
 Senemu
|
1359b6aba5
chat-persistent.sh : use bracket expressions in grep (#1564)
|
2 jaren geleden |
 Maarten ter Huurne
|
7d873811f3
Fix handling of "invalid property" when creating OpenCL command queue (#1565)
|
2 jaren geleden |
|
0cc4m
|
2e6cd4b025
OpenCL Token Generation Acceleration (#1459)
|
2 jaren geleden |
 Steward Garcia
|
7e4ea5beff
examples : add server example with REST API (#1443)
|
2 jaren geleden |
