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 12, 02:15 UTC
main
[refactor] CTMoEMethods to use QuantizationArgs (#28871)
HDCharles committed 11 months ago
[Bugfix] Follow-up fix on MediaWithBytes (#29951)
Roger Wang committed 11 months ago
[Bugfix][Quantization] Support BF16 tensors on GGUF (#29948)
Tsukasa OI committed 11 months ago
[CI/Build] Avoid duplicate empty inputs test for common multimodal generation tests (#29907)
Isotr0py committed 11 months ago
Isotr0py committed 11 months ago
[CI] Add Async Eplb nightly CI tests (#29385)
WeiQing Chen committed 11 months ago
[Refactor] [1/N] to simplify the vLLM serving architecture (#28040)
Chauncey committed 11 months ago
Add logging for cudagraph related info (#29825)
Yong Hoon Shin committed 11 months ago
[responsesAPI] support input output messages for non harmony models (#29549)
Andrew Xia committed 11 months ago
[Misc] Allow `fetch_*` utils to access local files by default (#29932)
Cyrus Leung committed 11 months ago
[BugFix] fix imgs_pos in hunyuan_vl (#29879)
JackieWu committed 11 months ago
[Bugfix] Defunctionalize TRTLLM AR+Norm op for avoiding extra clone kernel before it (#29631)
elvischenv committed 11 months ago
[Docs] Discuss api key limitations in security guide (#29922)
Russell Bryant committed 11 months ago
[Core] Rename PassConfig flags as per RFC #27995 (#29646)
Arpit Khandelwal committed 11 months ago
Andreas Karatzas committed 11 months ago
[Bugfix] Fix regression on pooling models from PR#29621 (#29921)
Roger Wang committed 11 months ago
[BugFix] Fix assert in `build_for_cudagraph_capture` (#29893)
Lucas Wilkinson committed 11 months ago
Reverting re-direction to amd_mi355_X. (#29914)
Alexei-V-Ivanov-AMD committed 11 months ago
[Doc] Add allocate_slots parameter docs (#29777)
maang-h committed 11 months ago
[ROCm][CI] Fix test_cudagraph_mode.py Failure For AMD CI (#29808)
Micah Williamson committed 11 months ago