 AlpinDale
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
hace 1 mes |
|
AlpinDale
|
22b8096006
misc: extend cuda graph capture size for H200 (#957)
|
hace 1 mes |
|
AlpinDale
|
5be6225f38
core: support multi-step scheduling w/ async post-processor (#955)
|
hace 1 mes |
|
AlpinDale
|
ea59784f59
tpu: remove torch._dynamo.reset() (#952)
|
hace 1 mes |
|
AlpinDale
|
0e2bfccda0
core: add virtual engine for async outproc (#939)
|
hace 1 mes |
|
AlpinDale
|
f1ea7711bd
core: do not compile ScalarType for torch < 2.4.0 (#938)
|
hace 1 mes |
|
AlpinDale
|
436d8fa0f1
core: do not compile for profiling (#931)
|
hace 1 mes |
|
AlpinDale
|
8d9f1fd4e6
feat: add single user mode (#927)
|
hace 1 mes |
|
AlpinDale
|
f7f3fed265
feat: add async postprocessor (#925)
|
hace 1 mes |
|
AlpinDale
|
132aa2abe4
spec decode: add support for EAGLE (#899)
|
hace 1 mes |
|
AlpinDale
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
hace 1 mes |
|
AlpinDale
|
abfd4465ca
feat: add support for chunked prefill + prefix caching (#871)
|
hace 1 mes |
|
AlpinDale
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
hace 1 mes |
|
AlpinDale
|
0a369f9171
feat: support chunked prefill with LoRA (#823)
|
hace 2 meses |
|
AlpinDale
|
0f1af04cf5
frontend: minor logging improvements (#787)
|
hace 2 meses |
|
AlpinDale
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
hace 4 meses |
|
AlpinDale
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
hace 4 meses |
|
AlpinDale
|
3693028340
feat: support for Audio modality (#698)
|
hace 4 meses |
|
AlpinDale
|
c2bb886b2e
fix: reinit procedure in `ModelInputForGPUBuilder` (#675)
|
hace 4 meses |
|
AlpinDale
|
bf88c8567e
feat: mamba model support (#674)
|
hace 4 meses |
|
AlpinDale
|
8583aefed7
chore: mamba cache single buffer (#673)
|
hace 4 meses |
|
AlpinDale
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
hace 4 meses |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hace 4 meses |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hace 8 meses |
|
AlpinDale
|
78d66f16d1
Chunked Prefill Part 1 (#384)
|
hace 9 meses |
|
AlpinDale
|
9181fa0396
feat: Triton kernels for sampling (#383)
|
hace 9 meses |
 AlpinDale
|
4b99ac15b7
fix: do not deepcopy metadata
|
hace 9 meses |
|
AlpinDale
|
17b034613d
chore: make metadata a dataclass (#377)
|
hace 9 meses |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
hace 9 meses |
 50h100a
|
b9e0ae87c5
fix fine-grained seeding.
|
hace 10 meses |
