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, 23:45 UTC
main
[TPU][TEST] Fix the downloading issue in TPU v1 test 11. (#21418)
QiliangCui committed over 1 year ago
Add test case for compiling multiple graphs (#21044)
Yong Hoon Shin committed over 1 year ago
[Core][Model] PrithviMAE Enablement on vLLM v1 engine (#20577)
Christian Pinto committed over 1 year ago
[Tests] Add tests for headless internal DP LB (#21450)
Nick Hill committed over 1 year ago
[Bugfix][Qwen][DCA] fixes bug in dual-chunk-flash-attn backend for qwen 1m models. (#21364)
Tao He committed over 1 year ago
[V1] Check all pooling tasks during profiling (#21299)
Cyrus Leung committed over 1 year ago
[Model] add Hunyuan V1 Dense Model support. (#21368)
Asher committed over 1 year ago
[Docs] Clean up v1/metrics.md (#21449)
Michael Yao committed over 1 year ago
[Misc] fixed nvfp4_moe test failures due to invalid kwargs (#21246)
Yang Chen committed over 1 year ago
Mamba V2 Test not Asserting Failures. (#21379)
Yu Chin Fabian Lim committed over 1 year ago
[Sampler] Introduce logprobs mode for logging (#21398)
Lu Fang committed over 1 year ago
[Docs] Fix bullets and grammars in tool_calling.md (#21440)
Michael Yao committed over 1 year ago
Fixed typo in profiling logs (#21441)
Sergio Paniego Blanco committed over 1 year ago
[Bugfix] ensure tool_choice is popped when `tool_choice:null` is passed in json payload (#19679)
Guillaume Calmettes committed over 1 year ago
add clear messages for deprecated models (#21424)
youkaichao committed over 1 year ago
[Cleanup] Only log MoE DP setup warning if DP is enabled (#21315)
Michael Goin committed over 1 year ago
[Core] Add basic unit test for maybe_evict_cached_block (#21400)
Jialin Ouyang committed over 1 year ago
[Bugfix] Fix nightly transformers CI failure (#21427)
Isotr0py committed over 1 year ago
Changing "amdproduction" allocation. (#21409)
Alexei-V-Ivanov-AMD committed over 1 year ago
[Bugfix][CUDA] fixes CUDA FP8 kv cache dtype supported (#21420)
elvischenv committed over 1 year ago