 AlpinDale
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
5 ヶ月 前 |
 AlpinDale
|
e7b1368156
feat: Phi3 support
|
6 ヶ月 前 |
|
AlpinDale
|
fca911ee0a
vLLM Upstream Sync (#526)
|
6 ヶ月 前 |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 ヶ月 前 |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 ヶ月 前 |
 sgsdxzy
|
6ebac34dc1
chore: cleaner pre-llamafied Yi implementation (#352)
|
9 ヶ月 前 |
|
AlpinDale
|
681e94611f
fix: restore backwards compatibility with old Yi models (#351)
|
9 ヶ月 前 |
|
AlpinDale
|
da223153c6
feat&fix: cohere support and missing GPU blocks (#333)
|
10 ヶ月 前 |
|
AlpinDale
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
10 ヶ月 前 |
|
AlpinDale
|
9810daa699
feat: INT8 KV Cache (#298)
|
10 ヶ月 前 |
|
AlpinDale
|
e31c6f0b45
feat: refactor modeling logic and support more models (#274)
|
10 ヶ月 前 |
|
AlpinDale
|
842912d022
feat: on-the-fly gguf conversion (#250)
|
11 ヶ月 前 |
|
AlpinDale
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
11 ヶ月 前 |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
11 ヶ月 前 |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 ヶ月 前 |
|
AlpinDale
|
f013d714c0
chore: merge dev branch into main (#177)
|
1 年間 前 |
|
AlpinDale
|
2755a48d51
merge dev branch into main (#153)
|
1 年間 前 |
|
AlpinDale
|
887e03669a
feat: add exllamav2 for GPTQ (#99)
|
1 年間 前 |
|
AlpinDale
|
74604eb252
fix: pylint complaints (#91)
|
1 年間 前 |
|
AlpinDale
|
efc6f7fbec
chore: reformats (#90)
|
1 年間 前 |
|
AlpinDale
|
a6a4220fa6
feat: refactor megatron and quants (#57)
|
1 年間 前 |
 50h100a
|
1da9efbcc7
restore rope scaling (#25)
|
1 年間 前 |
|
AlpinDale
|
0495c50a3e
GPTQ+exllama support (#21)
|
1 年間 前 |
|
AlpinDale
|
1ab15649ae
fix column parallelism in quantized layers
|
1 年間 前 |
|
AlpinDale
|
779148bfc3
fix missing import in llama modeling
|
1 年間 前 |
|
AlpinDale
|
75c27d3e65
massive overhaul
|
1 年間 前 |
|
AlpinDale
|
280583cd29
forgot import in llama code
|
1 年間 前 |
|
AlpinDale
|
d9c1d4f6e5
add awq support
|
1 年間 前 |
|
AlpinDale
|
22fe51d5c3
remove revision from llama for now
|
1 年間 前 |
|
AlpinDale
|
39beed0b87
Revert "Refactor AWQ support."
|
1 年間 前 |
