@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only
Fork 0

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 14, 05:30 UTC

Code Commits 22,390 Issues Pulls Cloud Agent CICD
main
main

[Core] Drop overly aggressive whisper assertion (#25408)

Russell Bryant committed about 1 year ago

f31ff87460

[Bugfix] fix custom op test (#25429)

Luka Govedič committed about 1 year ago

d588cd2406

[Frontend] Responses API MCP tools for built in tools and to pass through headers (#24628)

Alec S committed about 1 year ago

45d7d852d3

[TPU] update torch_xla dependency for PyPI compatibility (#25278)

Johnny Yang committed about 1 year ago

8bed179109

[CI/Build] Skip Qwen3-VL initialization tests until models are actually released (#25394)

Cyrus Leung committed about 1 year ago

f552d5e578

[KV offload][5/N] Add `CPUOffloadingSpec` (#24251)

Or Ozeri committed about 1 year ago

8db2939289

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

Luka Govedič committed about 1 year ago

d5e0fca264

[misc] Remove RFC review hours reference (#25416)

Simon Mo committed about 1 year ago

8d0ee5a564

[DP] support torchrun external launcher with Data Parallelism (#24899)

Lucia Fang committed about 1 year ago

922979bfcc

[CI Failure] Fix fp8 kv cache on <SM90 (#25396)

Michael Goin committed about 1 year ago

239ef0c1ac

[Compiler] Disable Inductor standalone compile by default (#25391)

ElizaWszola committed about 1 year ago

1d7f95b85c

[CLI env var] Add VLLM_FLASH_ATTN_MAX_NUM_SPLITS_FOR_CUDA_GRAPH in env variables (#25274)

Daisy-Ma-coder committed about 1 year ago

cfbee3d0e7

[EPLB] Reduce EPLB Inference Overhead (#24573)

Bowen Wang committed about 1 year ago

06a41334c7

[V1][Attention] Split triton_attn in triton-only and rocm specific backends (#24648)

Burkhard Ringlein committed about 1 year ago

175811e3b5

[Bugfix] Fix several issues with p2p xPyD in GET type (#23993)

Csrayz committed about 1 year ago

c10101a3eb

[Kernel] MI-300X triton moe configs (#23445)

Sara-KS committed about 1 year ago

ac243886b0

Make `mypy` behave like a proper pre-commit hook (#25313)

Harry Mellor committed about 1 year ago

3d2c56b7a9

Make pickle import check fast (#25379)

Harry Mellor committed about 1 year ago

64c824cd78

[Misc] Remove unused encoder-decoder error strings (#25374)

Cyrus Leung committed about 1 year ago

417a164af6

refactor: abstract graph mode support into platform interface (#25161)

Yizhou committed about 1 year ago

b6f01bd9a7
← Newer Page 633 of 1120 Older →