| .. |
|
adapter_commons
|
2f61644f6e
SPMD optimizations (#824)
|
hai 4 meses |
|
assets
|
653d1a08d4
feat: add support for audio models (#891)
|
hai 3 meses |
|
attention
|
f7f3fed265
feat: add async postprocessor (#925)
|
hai 3 meses |
|
common
|
d46e70ac98
api: add inline model loading (#928)
|
hai 2 meses |
|
distributed
|
2940da2c7b
distributed: fix custom allreduce p2p cache file generation (#922)
|
hai 3 meses |
|
endpoints
|
a3c03db735
fix: inline model loading conflicts with lora (#930)
|
hai 2 meses |
|
engine
|
15cb8d5c26
xpu: support pipeline parallel (#932)
|
hai 2 meses |
|
executor
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
hai 2 meses |
|
inputs
|
908ff753a1
fix: phi_3.5_v loading (#896)
|
hai 3 meses |
|
kv_quant
|
8a71788372
Add OLMoE (#772)
|
hai 5 meses |
|
lora
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
hai 2 meses |
|
modeling
|
c50309d386
model: add support for paligemma2 (#936)
|
hai 2 meses |
|
multimodal
|
03bd85c950
chore: multi-image support for llava-next (#935)
|
hai 2 meses |
|
platforms
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
hai 2 meses |
|
plugins
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
hai 3 meses |
|
processing
|
f7f3fed265
feat: add async postprocessor (#925)
|
hai 3 meses |
|
prompt_adapter
|
2f61644f6e
SPMD optimizations (#824)
|
hai 4 meses |
|
quantization
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
hai 2 meses |
|
server
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
hai 3 meses |
|
spec_decode
|
3b684a8a54
spec decode: streamline batch expansion tensor manipulation (#918)
|
hai 3 meses |
|
task_handler
|
15cb8d5c26
xpu: support pipeline parallel (#932)
|
hai 2 meses |
|
transformers_utils
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
hai 2 meses |
|
triton_utils
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 6 meses |
|
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 6 meses |
|
_core_ext.py
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
hai 6 meses |
|
_custom_ops.py
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
hai 2 meses |
|
_ipex_ops.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 6 meses |
|
connections.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
constants.py
|
2f61644f6e
SPMD optimizations (#824)
|
hai 4 meses |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
hai 1 ano |
|
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 6 meses |
|
version.py
|
8b8d2ce7e2
ci: bump aphrodite version to 0.6.4.post1 (#859)
|
hai 3 meses |
AlpinDale
c50309d386
model: add support for paligemma2 (#936)