| .. |
|
adapter_commons
|
2f61644f6e
SPMD optimizations (#824)
|
1 mese fa |
|
assets
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 mese fa |
|
attention
|
7a313483f1
chore: move update_flash_attn_metadata to attn backend (#731)
|
3 mesi fa |
|
common
|
483c9e6e59
fix: disable awq_marlin override for awq models (#843)
|
1 mese fa |
|
distributed
|
0f1af04cf5
frontend: minor logging improvements (#787)
|
2 mesi fa |
|
endpoints
|
dfa34d1b24
feat: add sampler_priorty (#837)
|
1 mese fa |
|
engine
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 mese fa |
|
executor
|
7c7ec12f36
chore: refactor executor classes for easier inheritance (#840)
|
1 mese fa |
|
inputs
|
2f61644f6e
SPMD optimizations (#824)
|
1 mese fa |
|
kv_quant
|
8a71788372
Add OLMoE (#772)
|
2 mesi fa |
|
lora
|
2f61644f6e
SPMD optimizations (#824)
|
1 mese fa |
|
modeling
|
dfa34d1b24
feat: add sampler_priorty (#837)
|
1 mese fa |
|
multimodal
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 mesi fa |
|
platforms
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
3 mesi fa |
|
plugins
|
f76f2a5af0
feat: add aphrodite plugin system (#705)
|
4 mesi fa |
|
processing
|
3d83e64f8e
feat: add metrics for prefix cache hit rate (#829)
|
1 mese fa |
|
prompt_adapter
|
2f61644f6e
SPMD optimizations (#824)
|
1 mese fa |
|
quantization
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 mese fa |
|
server
|
0256ed236b
feat: windows support (#790)
|
2 mesi fa |
|
spec_decode
|
16b587c104
fix: hidden states handling in batch expansion for spec decoding (#839)
|
1 mese fa |
|
task_handler
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 mese fa |
|
transformers_utils
|
fb96041ae3
fix: demote skip_special_tokens assertion to logger error (#778)
|
2 mesi fa |
|
triton_utils
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
_core_ext.py
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
3 mesi fa |
|
_custom_ops.py
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 mese fa |
|
_ipex_ops.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
connections.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 mese fa |
|
constants.py
|
2f61644f6e
SPMD optimizations (#824)
|
1 mese fa |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
1 anno fa |
|
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
version.py
|
22426653d3
ci: bump version to 0.6.4
|
1 mese fa |
AlpinDale
22426653d3
ci: bump version to 0.6.4