 AlpinDale
|
055c8905a3
api: add sampling/engine option to return only deltas or final output (#1035)
|
2 周之前 |
|
AlpinDale
|
411ac4f405
vlm: add support for Qwen2-VL model (#1015)
|
2 周之前 |
|
AlpinDale
|
09dab16f82
core: improve async postproc + multi-step performance (#983)
|
2 周之前 |
|
AlpinDale
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 周之前 |
|
AlpinDale
|
5be6225f38
core: support multi-step scheduling w/ async post-processor (#955)
|
2 周之前 |
|
AlpinDale
|
0e2bfccda0
core: add virtual engine for async outproc (#939)
|
2 周之前 |
|
AlpinDale
|
f7f3fed265
feat: add async postprocessor (#925)
|
3 周之前 |
|
AlpinDale
|
132aa2abe4
spec decode: add support for EAGLE (#899)
|
3 周之前 |
|
AlpinDale
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 周之前 |
|
AlpinDale
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 月之前 |
|
AlpinDale
|
2f61644f6e
SPMD optimizations (#824)
|
1 月之前 |
|
AlpinDale
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
4 月之前 |
|
AlpinDale
|
ef40c05cd3
fix: minor adjustments to scheduler and block manager (#667)
|
4 月之前 |
|
AlpinDale
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
4 月之前 |
|
AlpinDale
|
62111fab17
feat: allow serving encoder-decoder models in the API server (#664)
|
4 月之前 |
|
AlpinDale
|
a0e446a17d
feat: initial encoder-decoder support with BART model (#633)
|
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
|
9181fa0396
feat: Triton kernels for sampling (#383)
|
9 月之前 |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 月之前 |
|
AlpinDale
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
10 月之前 |
|
AlpinDale
|
9810daa699
feat: INT8 KV Cache (#298)
|
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
|
4d04ade9ef
feat: fine-grained seeds (#279)
|
10 月之前 |
|
AlpinDale
|
d2db4143fa
feat: add grafana for metrics (#240)
|
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
|
f013d714c0
chore: merge dev branch into main (#177)
|
1 年之前 |
|
AlpinDale
|
2755a48d51
merge dev branch into main (#153)
|
1 年之前 |
