 Georgi Gerganov
|
554b049068
flake.lock: Update (#9068)
|
1 year ago |
 ltoniazzi
|
2339a0be1c
tests : add integration test for lora adapters (#8957)
|
1 year ago |
 Yoshi Suhara
|
2fb9267887
Fix incorrect use of ctx_split for bias tensors (#9063)
|
1 year ago |
 Xuan Son Nguyen
|
8b3befc0e2
server : refactor middleware and /health endpoint (#9056)
|
1 year ago |
 tc-mb
|
d565bb2fd5
llava : support MiniCPM-V-2.6 (#8967)
|
1 year ago |
 Farbod Bijary
|
ee2984bdaf
py : fix wrong input type for raw_dtype in ggml to gguf scripts (#8928)
|
1 year ago |
 Aisuko
|
c8ddce8560
Fix inference example lacks required parameters (#9035)
|
1 year ago |
 compilade
|
23fd453544
gguf-py : bump version from 0.9.1 to 0.10.0 (#9051)
|
1 year ago |
 Minsoo Cheong
|
c679e0cb5c
llama : add EXAONE model support (#9025)
|
1 year ago |
 Liu Jia
|
fb487bb567
common : add support for cpu_get_num_physical_cores() on Windows (#8771)
|
1 year ago |
 Yoshi Suhara
|
2a24c8caa6
Add Nemotron/Minitron GGUF Conversion & Inference Support (#8922)
|
1 year ago |
 Nico Bosshard
|
e3f6fd56b1
ggml : dynamic ggml_sched_max_splits based on graph_size (#9047)
|
1 year ago |
 gtygo
|
4b9afbbe90
retrieval : fix memory leak in retrieval query handling (#8955)
|
1 year ago |
 Riceball LEE
|
37501d9c79
server : fix duplicated n_predict key in the generation_settings (#8994)
|
1 year ago |
 Zhenwei Jin
|
4af8420afb
common : remove duplicate function llama_should_add_bos_token (#8778)
|
1 year ago |
 Esko Toivonen
|
6bda7ce6c3
llama : add pre-tokenizer regexes for BLOOM and gpt3-finnish (#8850)
|
1 year ago |
|
Georgi Gerganov
|
d5492f0525
ci : disable bench workflow (#9010)
|
1 year ago |
 Jiří Podivín
|
234b30676a
server : init stop and error fields of the result struct (#9026)
|
1 year ago |
 0cc4m
|
5fd89a70ea
Vulkan Optimizations and Fixes (#8959)
|
1 year ago |
|
compilade
|
98a532d474
server : fix segfault on long system prompt (#8987)
|
1 year ago |
|
Georgi Gerganov
|
43bdd3ce18
cmake : remove unused option GGML_CURL (#9011)
|
1 year ago |
 Daniel Bevenius
|
06943a69f6
ggml : move rope type enum to ggml.h (#8949)
|
1 year ago |
|
Xuan Son Nguyen
|
828d6ff7d7
export-lora : throw error if lora is quantized (#9002)
|
1 year ago |
 Diogo Teles Sant'Anna
|
fc4ca27b25
ci : fix github workflow vulnerable to script injection (#9008)
|
1 year ago |
 Radoslav Gerganov
|
1f67436c5e
ci : enable RPC in all of the released builds (#9006)
|
1 year ago |
|
Nico Bosshard
|
0fd93cdef5
llama : model-based max number of graph nodes calculation (#8970)
|
1 year ago |
 Frank Mai
|
84eb2f4fad
docs: introduce gpustack and gguf-parser (#8873)
|
1 year ago |
 DavidKorczynski
|
1262e7ed13
grammar-parser : fix possible null-deref (#9004)
|
1 year ago |
|
DavidKorczynski
|
df5478fbea
ggml: fix div-by-zero (#9003)
|
1 year ago |
|
Liu Jia
|
2589292cde
Fix a spelling mistake (#9001)
|
1 year ago |
