 AlpinDale
|
9fc6473b18
server: log the process occupying our port (#866)
|
преди 1 месец |
|
AlpinDale
|
0f1af04cf5
frontend: minor logging improvements (#787)
|
преди 2 месеца |
|
AlpinDale
|
0256ed236b
feat: windows support (#790)
|
преди 2 месеца |
 50h100a
|
371d57af82
filesize-driven progress bar for loading tensors
|
преди 2 месеца |
|
AlpinDale
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
преди 4 месеца |
|
AlpinDale
|
5d37ec1016
suppress tpu import warning (#696)
|
преди 4 месеца |
|
AlpinDale
|
4fe371b7fa
fix: allow passing float for GiB arguments (#690)
|
преди 4 месеца |
|
AlpinDale
|
3f712cd287
feat: add progress bar for loading individual weight modules (#640)
|
преди 4 месеца |
|
AlpinDale
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
преди 4 месеца |
|
AlpinDale
|
62111fab17
feat: allow serving encoder-decoder models in the API server (#664)
|
преди 4 месеца |
|
AlpinDale
|
0e5bb11503
fix: make `merge_async_iterators.is_cancelled()` optional (#656)
|
преди 4 месеца |
|
AlpinDale
|
a2344d3617
fix: move zeromq rpc frontend to IPC instead of TCP (#652)
|
преди 4 месеца |
|
AlpinDale
|
31f82da8bd
chore: deduplicate nvlink check to cuda platform (#643)
|
преди 4 месеца |
|
AlpinDale
|
77c4fbd5c9
fix: better async request cancellation (#641)
|
преди 4 месеца |
|
AlpinDale
|
308501daa5
fix: default api port and attention selector (#634)
|
преди 4 месеца |
|
AlpinDale
|
a0e446a17d
feat: initial encoder-decoder support with BART model (#633)
|
преди 4 месеца |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
преди 4 месеца |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
преди 8 месеца |
|
AlpinDale
|
e3252edd07
fix: remove event and stream, add typing (#382)
|
преди 9 месеца |
|
AlpinDale
|
33b3786175
fix: cache neuron checks (#379)
|
преди 9 месеца |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
преди 9 месеца |
 AlpinDale
|
e53842bd5d
fix: cuda home detection for fp8 kv cache
|
преди 9 месеца |
|
AlpinDale
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
преди 10 месеца |
|
AlpinDale
|
c2d77b1822
chore: logging refactor (#302)
|
преди 10 месеца |
|
AlpinDale
|
9810daa699
feat: INT8 KV Cache (#298)
|
преди 10 месеца |
|
AlpinDale
|
ea0f57b233
feat: allow further support for non-cuda devices (#247)
|
преди 11 месеца |
|
AlpinDale
|
31c95011a6
feat: FP8 E5M2 KV Cache (#226)
|
преди 11 месеца |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
преди 11 месеца |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
преди 11 месеца |
|
AlpinDale
|
f013d714c0
chore: merge dev branch into main (#177)
|
преди 1 година |
