Pinned Loading
-
-
-
x-failures-to-1000-users
x-failures-to-1000-users PublicI document my failures until I succeed in building something with 1000 users.
HCL
-
vllm-qwen3-8-27b-fp8-l40s-kernel-config-tuning
vllm-qwen3-8-27b-fp8-l40s-kernel-config-tuning PublicTuning vLLM's dense W8A8 block-FP8 Triton GEMM kernel for Qwen3.8-27B-FP8 on NVIDIA L40S.
HTML
-
vllm-project/vllm
vllm-project/vllm PublicA high-throughput and memory-efficient inference and serving engine for LLMs
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.



