| .. |
|
adapter_commons
|
2f61644f6e
SPMD optimizations (#824)
|
4 mēneši atpakaļ |
|
assets
|
653d1a08d4
feat: add support for audio models (#891)
|
3 mēneši atpakaļ |
|
attention
|
f7f3fed265
feat: add async postprocessor (#925)
|
3 mēneši atpakaļ |
|
common
|
f7f3fed265
feat: add async postprocessor (#925)
|
3 mēneši atpakaļ |
|
distributed
|
2940da2c7b
distributed: fix custom allreduce p2p cache file generation (#922)
|
3 mēneši atpakaļ |
|
endpoints
|
53d0ba7c7c
api: add endpoint for loading and unloading the model (#926)
|
3 mēneši atpakaļ |
|
engine
|
f7f3fed265
feat: add async postprocessor (#925)
|
3 mēneši atpakaļ |
|
executor
|
0c6d90dade
neuron: add support for tensor parallelism (#923)
|
3 mēneši atpakaļ |
|
inputs
|
908ff753a1
fix: phi_3.5_v loading (#896)
|
3 mēneši atpakaļ |
|
kv_quant
|
8a71788372
Add OLMoE (#772)
|
5 mēneši atpakaļ |
|
lora
|
369600855a
xpu: disable punica kernels for XPU (#864)
|
3 mēneši atpakaļ |
|
modeling
|
5cb2e998d8
quants: update compressed tensors lifecycle to remove `prefix` from `create_weights` (#924)
|
3 mēneši atpakaļ |
|
multimodal
|
653d1a08d4
feat: add support for audio models (#891)
|
3 mēneši atpakaļ |
|
platforms
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
6 mēneši atpakaļ |
|
plugins
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 mēneši atpakaļ |
|
processing
|
f7f3fed265
feat: add async postprocessor (#925)
|
3 mēneši atpakaļ |
|
prompt_adapter
|
2f61644f6e
SPMD optimizations (#824)
|
4 mēneši atpakaļ |
|
quantization
|
f7f3fed265
feat: add async postprocessor (#925)
|
3 mēneši atpakaļ |
|
server
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 mēneši atpakaļ |
|
spec_decode
|
3b684a8a54
spec decode: streamline batch expansion tensor manipulation (#918)
|
3 mēneši atpakaļ |
|
task_handler
|
f7f3fed265
feat: add async postprocessor (#925)
|
3 mēneši atpakaļ |
|
transformers_utils
|
132aa2abe4
spec decode: add support for EAGLE (#899)
|
3 mēneši atpakaļ |
|
triton_utils
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mēneši atpakaļ |
|
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mēneši atpakaļ |
|
_core_ext.py
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
6 mēneši atpakaļ |
|
_custom_ops.py
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
3 mēneši atpakaļ |
|
_ipex_ops.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mēneši atpakaļ |
|
connections.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
4 mēneši atpakaļ |
|
constants.py
|
2f61644f6e
SPMD optimizations (#824)
|
4 mēneši atpakaļ |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
1 gadu atpakaļ |
|
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mēneši atpakaļ |
|
version.py
|
8b8d2ce7e2
ci: bump aphrodite version to 0.6.4.post1 (#859)
|
3 mēneši atpakaļ |
AlpinDale
53d0ba7c7c
api: add endpoint for loading and unloading the model (#926)