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 3, 01:45 UTC
main
[Frontend] Add truncation side to OpenAI endpoints (#43260)
ruizhang committed 5 months ago
[ROCm][CI] add warmup to mem_util test before measurement (#43236)
Divakar Verma committed 5 months ago
[ROCm] Add XGMI backend for MoRI Connector (#41753)
Simon Danielsson committed 5 months ago
[Bugfix] Fix DSV4 Base model swiglu limit issue in FP8 path (#42855)
Chengze Fan committed 5 months ago
[CI] Fix dockerfile dependency graph failure for pre-commit (#43378)
Isotr0py committed 5 months ago
[Rust Frontend] Move code from `vllm-frontend-rs` (#43283)
Bugen Zhao committed 6 months ago
[Bugfix] Zero stale is_prefilling in padded CUDA graph rows for Mamba (#41873)
Lanze Liu committed 6 months ago
[BugFix] Use correct logprobs for `logprob_token_ids` (#43125)
Nick Hill committed 6 months ago
[Feature] Add `--cpu-distributed-timeout-seconds` CLI Option for CPU Process Group Timeout (#42968)
fangyuchu committed 6 months ago
[Frontend] Rework fastokens integration (#43168)
Nick Hill committed 6 months ago
Disable build isolation to bypass CUDA related deps for vllm-tpu (#43038)
ylangtsou committed 6 months ago
[Core] Add native ModelExpress load format (#43105)
Zheng Luo committed 6 months ago
[Perf] `zeros` -> `empty` to remove additional fill (#42988)
Wentao Ye committed 6 months ago
[Deprecation] Mark env vars covered by --moe-backend / --linear-backend (#43148)
Michael Goin committed 6 months ago
[Bugfix] Add early validation to reject incompatible runner types for embedding models (#43079)
anish committed 6 months ago
[CI] Fix CPU tests failing on `tl.exp2` import (#43311)
haosdent committed 6 months ago
[Perf] [Hybrid] Fused Triton kernel for GPU-side Mamba state postprocessing (#40172)
Francesco Fusco committed 6 months ago
[CPU][RISC-V] Add VLEN=256 support to RVV attention kernels (#42943)
velonica0 committed 6 months ago
[XPU][CI]Fix Docker image pull-to-run race in Intel GPU CI (#43266)
xiangdong committed 6 months ago
[CI] Pin protoc binary in rust-build stages (#43292)
haosdent committed 6 months ago