AlpinDale 5bec8fbb1b tpu: add support for async postprocessing (#968) пре 2 месеци
..
adapter_commons 2f61644f6e SPMD optimizations (#824) пре 3 месеци
assets 653d1a08d4 feat: add support for audio models (#891) пре 2 месеци
attention d6cbbba95f Revert "fix: issues with flashinfer fp8 kv (#950)" (#956) пре 2 месеци
common 5bec8fbb1b tpu: add support for async postprocessing (#968) пре 2 месеци
compilation 0e5cf7f840 tpu: avoid dynamo guard eval overhead (#949) пре 2 месеци
distributed 2940da2c7b distributed: fix custom allreduce p2p cache file generation (#922) пре 2 месеци
endpoints 39b2e83ac3 api: optimize zeromq frontend performance (#951) пре 2 месеци
engine 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) пре 2 месеци
executor 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) пре 2 месеци
inputs 908ff753a1 fix: phi_3.5_v loading (#896) пре 2 месеци
kv_quant 8a71788372 Add OLMoE (#772) пре 5 месеци
lora bf4a4d8516 fix: do not register punica with torch if using older torch (#948) пре 2 месеци
modeling a8bdd488b9 distributed: support pipeline parallelism for internvl and internlm2 (#965) пре 2 месеци
multimodal 2aabf8fcf7 vlm: fix errors on ragged NestedTensors (#953) пре 2 месеци
platforms 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934) пре 2 месеци
plugins 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) пре 2 месеци
processing 5be6225f38 core: support multi-step scheduling w/ async post-processor (#955) пре 2 месеци
prompt_adapter 2f61644f6e SPMD optimizations (#824) пре 3 месеци
quantization 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) пре 2 месеци
server 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) пре 2 месеци
spec_decode 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) пре 2 месеци
task_handler 5bec8fbb1b tpu: add support for async postprocessing (#968) пре 2 месеци
transformers_utils 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934) пре 2 месеци
triton_utils f1d0b77c92 [0.6.0] Release Candidate (#481) пре 6 месеци
__init__.py f1d0b77c92 [0.6.0] Release Candidate (#481) пре 6 месеци
_core_ext.py f1ea7711bd core: do not compile ScalarType for torch < 2.4.0 (#938) пре 2 месеци
_custom_ops.py fcfcfc65e1 quants: add triton kernels for AWQ (#946) пре 2 месеци
_ipex_ops.py f1d0b77c92 [0.6.0] Release Candidate (#481) пре 6 месеци
connections.py c6c91edab7 ci: update & overhaul test units (#769) пре 3 месеци
constants.py 2f61644f6e SPMD optimizations (#824) пре 3 месеци
py.typed 1c988a48b2 fix logging and add py.typed пре 1 година
scalar_type.py f1d0b77c92 [0.6.0] Release Candidate (#481) пре 6 месеци
version.py cbd51a208a ci: bump to 0.6.5 (#964) пре 2 месеци