[FrontEnd] UNREVERT CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops (#26502)

Morrison Turnansky committed about 1 year ago

[Bug] Fix Assertion error DeepEP/csrc/kernels/intranode.cu:928: 'false and Unsupported type' (#26532)

Wentao Ye committed about 1 year ago

[CI Perf]Prune Tests in kernel/mamba (#26538)

Fardin Hoque committed about 1 year ago

[CI] Fix mypy for `vllm/distributed` (#26593)

Wentao Ye committed about 1 year ago

[Frontend][1/N] Improve all pooling task | Support FP16 Embedding Base64 (Still uses fp32 by default). (#26414)

wang.yuqi committed about 1 year ago

[Quantization] [Performance] Enable Marlin GEMM kernels for the calibration-free RTN-based quantization (#26051)

Alex Kogan committed about 1 year ago

[CI][Release][Arm64]: Build arm64 release for gpu arch 8.9 (#26698)

Yibo Cai committed about 1 year ago

[Log] Optimize Startup Log (#26601)

Wentao Ye committed about 1 year ago

[Model] Use merge_by_field_config for MM models (M-N) (#26710)

Cyrus Leung committed about 1 year ago

[Bugfix][Speculative Decoding] Extend Eagle quantization config fix to llama_eagle.py (#26590)

Rahul Tuli committed about 1 year ago

[Bugfix][Rocm] fix qr error when different inp shape (#25892)

haoyangli-amd committed about 1 year ago

[CI/Build] upgrade compressed-tensors to 0.12.2 to address LGPLv3 (#26501)

Sangyeon Cho committed about 1 year ago

[Misc] Separate prompt logging to debug (#26713)

Aleksei Tsvetkov committed about 1 year ago

[P/D] [NixlConnector] kv load recovery integration (#26171)

Will Eaton committed about 1 year ago

[UX] Speedup DeepGEMM warmup with heuristics (#25619)

Michael Goin committed about 1 year ago

[FEATURE]: Use pydantic validation in `multimodal.py` config (#26629)

Anand Roy committed about 1 year ago

[Hardware][CPU] Disable torch.compile for RISC-V to prevent APIError (#26693)

ihb2032 committed about 1 year ago

[unrevert] Add batch invariant kernel override for FlashInfer backend [2/n] (#26373)

Bram Wasti committed about 1 year ago

[Bugfix] Fix out of bound index issue for Jina-embedding-v3 RoPE with cuda graph (#26687)

Isotr0py committed about 1 year ago

[ResponseAPI] Simplify input/output message serialization (#26620)

Jialin Ouyang committed about 1 year ago