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 15, 23:30 UTC
main
[Bugfix][AMD] Update torch_bindings so that scaled_fp4_quant isn't build on ROCm (#13235)
Sage Moore committed almost 2 years ago
[V1][PP] Fix memory profiling in PP (#13315)
Woosuk Kwon committed almost 2 years ago
[V1][Sampler] Don't apply temp for greedy-only (#13311)
Nick Hill committed almost 2 years ago
[V1][CI] Fix failed v1-test because of min_p (#13316)
Woosuk Kwon committed almost 2 years ago
[V1][Core] min_p sampling support (#13191)
Aoyu committed almost 2 years ago
[Core] Reduce TTFT with concurrent partial prefills (#10235)
Joe Runde committed almost 2 years ago
[Quant][Perf] Use moe_wna16 kernel by default for MoEs with many experts (#13236)
Michael Goin committed almost 2 years ago
[Hardware][Gaudi][Bugfix] Fix error for guided decoding (#12317)
Yu-Zhou committed almost 2 years ago
[Core] choice-based structured output with xgrammar (#12632)
Russell Bryant committed almost 2 years ago
Support logit_bias in v1 Sampler (#13079)
Lu Fang committed almost 2 years ago
[V1] Simplify GPUModelRunner._update_states check (#13265)
Nick Hill committed almost 2 years ago
[VLM] Keep track of whether prompt replacements have been applied (#13215)
Cyrus Leung committed almost 2 years ago
[Misc] Log time consumption of sleep and wake-up (#13115)
Jun Duan committed almost 2 years ago
[Bugfix] Fix missing parentheses (#13263)
Xu Song committed almost 2 years ago
[Frontend] Optionally remove memory buffer used for uploading to URLs in run_batch (#12927)
Pooya Davoodi committed almost 2 years ago
[WIP] TPU V1 Support Refactored (#13049)
Alexander Matveev committed almost 2 years ago
Kero Liang committed almost 2 years ago
[ROCm][V1] Add intial ROCm support to V1 (#12790)
Sage Moore committed almost 2 years ago
[V1] LoRA - Enable Serving Usecase (#12883)
Varun Sundar Rabindranath committed almost 2 years ago
Expand MLA to support most types of quantization (#13181)
Michael Goin committed almost 2 years ago