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, 17:15 UTC
main
[Hardware][TPU] Skip failed compilation test (#15421)
Siyuan Liu committed over 1 year ago
[BugFix][V1] Quick fix for min_tokens with multiple EOS (#15407)
Nick Hill committed over 1 year ago
[V1][Perf] Simpler request output queues (#15156)
Nick Hill committed over 1 year ago
[Doc] Update docs on handling OOM (#15357)
Cyrus Leung committed over 1 year ago
[DOC] Add Kubernetes deployment guide with CPUs (#14865)
Yuan Tang committed over 1 year ago
[Hardware][Gaudi][Feature] Enable Dynamic MoE for Mixtral (#12303)
liuzhenwei committed over 1 year ago
[V1] Aggregate chunked prompt logprobs in model runner (#14875)
Nick Hill committed over 1 year ago
[MISC] Refine no available block debug msg (#15076)
Yi Liu committed over 1 year ago
[V1][Minor] fix comments (#15392)
Chen1022 committed over 1 year ago
[Core] Don't force uppercase for VLLM_LOGGING_LEVEL (#15306)
Russell Bryant committed over 1 year ago
[Core] Integrate `fastsafetensors` loader for loading model weights (#10647)
Manish Sethi committed over 1 year ago
[distributed] fix dp group (#15355)
youkaichao committed over 1 year ago
[Bugfix] Fix chat template loading (#15143)
Cyrus Leung committed over 1 year ago
Fix zmq IPv6 URL format error (#15341)
Russell Bryant committed over 1 year ago
[Kernel] allow non-contiguous input for marlin kernel (#14658)
Jinzhen Lin committed over 1 year ago
Revert "[CI/Build] Use uv python for docker rather than ppa:deadsnakess/ppa (#13569)" (#15377)
Simon Mo committed over 1 year ago
[Misc] Update guided decoding logs to debug (#15310)
sfbemerk committed over 1 year ago
[Bugfix][V1] Avoid importing PreTrainedModel (#15366)
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 committed over 1 year ago
[Misc] Remove ignore_reinit_error for ray.init() (#15373)
Rui Qiao committed over 1 year ago
[Misc] Upgrade BNB version (#15183)
Jee Jee Li committed over 1 year ago