 50h100a
|
bd564148e2
Merge branch 'main' of https://github.com/PygmalionAI/aphrodite-engine into ffs
|
9 months ago |
|
50h100a
|
d3dd170a7d
merge main
|
9 months ago |
 AlpinDale
|
78d66f16d1
Chunked Prefill Part 1 (#384)
|
9 months ago |
|
AlpinDale
|
9181fa0396
feat: Triton kernels for sampling (#383)
|
9 months ago |
 50h100a
|
dc09dc2b4d
Merge branch 'main' into pr_samplers
|
9 months ago |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 months ago |
|
50h100a
|
7ed57e318d
Overhauled SamplingTensors construction.
|
9 months ago |
|
50h100a
|
d5dbd29db4
hoist sampler internals into a single function.
|
9 months ago |
|
AlpinDale
|
da223153c6
feat&fix: cohere support and missing GPU blocks (#333)
|
9 months ago |
|
AlpinDale
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
10 months ago |
|
AlpinDale
|
9fa99215f8
feat: add cubic sampling (#280)
|
10 months ago |
|
AlpinDale
|
657aec0cbd
refactor: OpenAI endpoint (#261)
|
10 months ago |
|
AlpinDale
|
4d04ade9ef
feat: fine-grained seeds (#279)
|
10 months ago |
 anon998
|
35b9033782
fix: crash in quadratic sampling when batch > 1 (#253)
|
11 months ago |
|
50h100a
|
f619c96c79
fix: zero token output due to temperature bias (#243)
|
11 months ago |
|
50h100a
|
53a9c60442
fix: logit processor declarations and application (#242)
|
11 months ago |
|
50h100a
|
2e3318c1fa
yapf considers this space to be CRITICAL
|
11 months ago |
|
50h100a
|
25acebe33d
better variable naming
|
11 months ago |
|
50h100a
|
7b3bb995c1
topk as linear write
|
11 months ago |
|
AlpinDale
|
e73a92ad2f
fix: remove the mask for quadratic sampling (#236)
|
11 months ago |
|
AlpinDale
|
1c46fa31ad
feat: add quadratic sampling (#233)
|
11 months ago |
|
AlpinDale
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
11 months ago |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
11 months ago |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 months ago |
 Stefan Gligorijevic
|
9e7e108dc8
chore: clamp dynatemp_min (#214)
|
11 months ago |
|
Stefan Gligorijevic
|
56446a04bb
feat: dynamic temperature (#209)
|
11 months ago |
|
AlpinDale
|
d54791aaa8
feat: reduce sampler overhead by making it less blocking (#198)
|
1 year ago |
|
AlpinDale
|
653da510d1
chore: rewrite InputMetadata (#143)
|
1 year ago |
|
AlpinDale
|
6c914ea0e4
fix: `SequenceOutputs` -> `SequenceOutput` (#133)
|
1 year ago |
|
Stefan Gligorijevic
|
a5255901c6
feat: min_p sampling (#106)
|
1 year ago |
