 AlpinDale
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 周之前 |
|
AlpinDale
|
901900854e
chore: consolidate environment variables within one file (#882)
|
4 周之前 |
|
AlpinDale
|
b5aa11020b
api: fix crashes under very high loads (#878)
|
4 周之前 |
|
AlpinDale
|
5bd4473bb6
async: avoid premature exit in the async generator (#872)
|
1 月之前 |
|
AlpinDale
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 月之前 |
 AlpinDale
|
dcb794a340
fix: revert incorrect commit
|
2 月之前 |
|
AlpinDale
|
76367b5ae7
wip
|
2 月之前 |
|
AlpinDale
|
9d9722b1c1
fix: metrics endpoint with RPC server (#747)
|
3 月之前 |
|
AlpinDale
|
7debd35ca2
fix: shut down ray dag workers cleanly (#692)
|
4 月之前 |
|
AlpinDale
|
19ad952dd4
chore: better stream termination in async engine (#672)
|
4 月之前 |
|
AlpinDale
|
62111fab17
feat: allow serving encoder-decoder models in the API server (#664)
|
4 月之前 |
|
AlpinDale
|
ed9a6f97c1
fix: kill api server when pinging dead engine (#660)
|
4 月之前 |
|
AlpinDale
|
77c4fbd5c9
fix: better async request cancellation (#641)
|
4 月之前 |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 月之前 |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 月之前 |
|
AlpinDale
|
0f6d56b07f
feat: model executor refactor (#367)
|
9 月之前 |
|
AlpinDale
|
b361096463
fix: tokenizer when using ray (#366)
|
9 月之前 |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 月之前 |
|
AlpinDale
|
c2d77b1822
chore: logging refactor (#302)
|
10 月之前 |
|
AlpinDale
|
2d3d44b3e9
chore: add health check for ray workers (#290)
|
10 月之前 |
|
AlpinDale
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
10 月之前 |
|
AlpinDale
|
657aec0cbd
refactor: OpenAI endpoint (#261)
|
10 月之前 |
|
AlpinDale
|
6a63ab4ec3
fix: remote encode request if using ray (#270)
|
10 月之前 |
|
AlpinDale
|
c0146ed00e
chore: slight refactor for async engine finish (#225)
|
11 月之前 |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
11 月之前 |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 月之前 |
|
AlpinDale
|
b9b295d74e
chore: backlogs 1 (#191)
|
1 年之前 |
|
AlpinDale
|
980673ffb7
fix: fractional gpus (#157)
|
1 年之前 |
|
AlpinDale
|
e7b6a2d5a0
chore: tensor parallel refactors part 2 (#116)
|
1 年之前 |
|
AlpinDale
|
035878898f
bug: minor ray issue
|
1 年之前 |
