A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 00:00 UTC
main
[Kernel] [Helion] [6/N] Add num_tokens dimension to silu_mul autotuning and dispatching (#34185)
Yanan Cao committed 9 months ago
Ensure that MkDocs v2 does not get installed (#34958)
Harry Mellor committed 9 months ago
[perf] Avoid dtype promotion sync in mamba_get_block_table_tensor (#34870)
Huamin Li committed 9 months ago
[Refactor] Extract Harmony streaming SSE event builders into streaming_events.py (#34909)
Flora Feng committed 9 months ago
[V0 Deprecation] Remove unused MM placeholders in request output (#34944)
Cyrus Leung committed 9 months ago
[BUGFIX] Fix `_dummy_run` missing `prepare_inputs_event` synchronization (#34866)
Vadim Gimpelson committed 9 months ago
[Kernel] Optimize grouped topk kernel (#34206)
Xin Yang committed 9 months ago
[Bugfix][Hardware][AMD] Fix ROCM_AITER_FA speculative decoding support (#32877)
Kevin McKay committed 9 months ago
[Minor] Add logging when using MXFP4 MXFP8 TRTLLM backend (#34916)
Frank Wang committed 9 months ago
[Models] LFM2: Support LoRA (#34921)
tianshu-Michael-yu committed 9 months ago
[ROCm][CI] Loosen RemoteOpenAIServer Startup Timeout (#34922)
Micah Williamson committed 9 months ago
[Misc] Add deprecated environment variable utilities (#33677)
杨朱 · Kiki committed 9 months ago
[CI][AMD][BugFix][P/D] Add default_vllm_config to test_moriio_connector.py so tests pass (#33739)
rasmith committed 9 months ago
Add validation to reject non-text content in system messages (#34072)
Varun Chawla committed 9 months ago
[Model Bash]: Improve FP8 Oracle for Config Specific Kernel Selection (#34260)
Elizabeth Thomas committed 9 months ago
[Bugfix] Add regression test for MoE quant_config under torch.compile (#34335)
Matthias Gehre committed 9 months ago
[Quark] Fix MoE fp8 activation scale handling on mi300 (#34386)
Bowen Bao committed 9 months ago
[ci] Use the right tag for CPU arm64 image (#34915)
Kevin H. Luu committed 9 months ago
[Refactor] Implement output type check in LLM (#34794)
Cyrus Leung committed 9 months ago
[Core] Fix state names in pause_scheduler() (#34840)
Mark McLoughlin committed 9 months ago