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, 14:13 UTC
main
Cyrus Leung committed 9 months ago
[Perf] Optimize detokenizer python logic (#32975)
Wentao Ye committed 9 months ago
[BugFix] Avoid prefix cache hit in the same schedule step for mamba layers (#29387)
Chen Zhang committed 9 months ago
[Frontend][CI] Consolidate instrumentator entrypoints (#34123)
wang.yuqi committed 9 months ago
[Bugfix] Sort hf_weights_files in fastsafetensors_weights_iterator to match #33491 (#34190)
Balaxxe committed 9 months ago
[responsesAPI] fix simpleContext streaming output_messages (#34188)
Andrew Xia committed 9 months ago
[Bugfix] Add `--trust-remote-code` to dataset bench args (#34208)
Cyrus Leung committed 9 months ago
[Bugfix] Fix DP Attention Padding in Dummy Run (#34187)
Lucas Wilkinson committed 9 months ago
[CI/Build] Relax `test_mcp_tool_call` (#34204)
Cyrus Leung committed 9 months ago
[Doc] Update usage of `--limit-mm-per-prompt` (#34148)
Cyrus Leung committed 9 months ago
[Bugfix][Core] Fix CPU memory leak from Request reference cycle in prefix caching (#34183)
Roger Wang committed 9 months ago
[ROCm][Bugfix] Resolve Dynamo tracing crash from amdsmi calls in on_gfx* arch detection (#34108)
Andreas Karatzas committed 9 months ago
[Bugfix] Adopt `ChunkGatedDeltaRule` for Qwen3.5 (#34198)
Roger Wang committed 9 months ago
[LMCache] Token Base IPC API (#34175)
Yuwei An committed 9 months ago
[structured output] validate unsupported json features first (#33233)
Ning Xie committed 9 months ago
Gregory Shtrasberg committed 9 months ago
[Doc] Add DCP support to attention backend doc (#33936)
Michael Goin committed 9 months ago
[ModelRunner V2][BugFix] Fix `max_query_len` calculation (#34167)
Nick Hill committed 9 months ago
[torch.compile][Fusion] Fix attention fusion pass removing kv_udpate op. (#33945)
Charlie Fu committed 9 months ago
[ROCm] update triton branch to support gpt-oss models for gfx11xx devices (#34032)
Hongxia Yang committed 9 months ago