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, 16:00 UTC
main
[Attention] Refactor FA `block_size` limitations to hybrid models only (#29084)
Nicolò Lucchesi committed 12 months ago
[tiny] Remove unsupported TRITON_MLA backend from batch invariance (#28832)
Bram Wasti committed 12 months ago
fix: clean up function never use in setup.py (#29061)
yihong committed 12 months ago
Fix: Resolve circular import in model_loader/utils.py (#29189)
Nandan Vallamdasu committed 12 months ago
[Misc] Further clean up chunked prefill and prefix caching init (#29186)
Cyrus Leung committed 12 months ago
[CI/Build Don't add FLASHINFER backend in test_cpu_offloading.py (#29229)
rasmith committed 12 months ago
[CI/Build] Skip tests that require libcudart in test_lmcache_integration.py (#29228)
rasmith committed 12 months ago
Simplify `from_blob` usage in `get_cuda_view_from_cpu_tensor` (#29027)
Jane (Yuan) Xu committed 12 months ago
Handle triton kernel import exception (#29062)
jinghanhu committed 12 months ago
Mads Kildegård committed 12 months ago
[responsesAPI] parse reasoning item input (#28248)
Andrew Xia committed 12 months ago
[Model Runner V2] Limit cudagraph size to max decode batch size (#29221)
Woosuk Kwon committed 12 months ago
[LoRA] Cleanup FusedMoEWithLoRA (#29187)
Jee Jee Li committed 12 months ago
[Bugfix]Fix a conditional to not check zero value (#28754)
Yanan Cao committed 12 months ago
[CI/Build] Only use supported types and features on ROCm in MoE kernel tests (#29149)
rasmith committed 12 months ago
[chore][LMCache connector] Remove useless logs from lmcache connector (#29069)
Yihua Cheng committed 12 months ago
[CI/Build][AMD] Enable Entrypoints Integration Test (Pooling) to run without error on ROCm (#29212)
rasmith committed 12 months ago
Add fused MoE config for H200 E160 N192 fp8 (#29182)
FlintyLemming committed 12 months ago
[CI/Build] Disable test_gptoss_tp.py in 'LoRA TP Test' group for ROCm platform (#29204)
qli88 committed 12 months ago
[Bugfix] Fix block size in block_table with PCP (#29094)
Jie Luo committed 12 months ago