init

366dfe82 · jixx · 366dfe82 · 366dfe82 · 366dfe82 · 366dfe82
Commit 366dfe82 authored Nov 20, 2024 by jixx
20 changed files
--- a/router/src/infer/v3/block_allocator.rs
+++ b/router/src/infer/v3/block_allocator.rs
--- a/router/src/infer/v3/mod.rs
+++ b/router/src/infer/v3/mod.rs
--- a/router/src/infer/v3/queue.rs
+++ b/router/src/infer/v3/queue.rs
--- a/router/src/infer/v3/scheduler.rs
+++ b/router/src/infer/v3/scheduler.rs
--- a/router/src/kserve.rs
+++ b/router/src/kserve.rs
--- a/router/src/lib.rs
+++ b/router/src/lib.rs
--- a/router/src/main.rs
+++ b/router/src/main.rs
--- a/router/src/server.rs
+++ b/router/src/server.rs
--- a/router/src/validation.rs
+++ b/router/src/validation.rs
--- a/rust-toolchain.toml
+++ b/rust-toolchain.toml
--- a/sagemaker-entrypoint.sh
+++ b/sagemaker-entrypoint.sh
--- a/server/.gitignore
+++ b/server/.gitignore
--- a/server/Makefile
+++ b/server/Makefile
--- a/server/Makefile-awq
+++ b/server/Makefile-awq
--- a/server/Makefile-eetq
+++ b/server/Makefile-eetq
--- a/server/Makefile-lorax-punica
+++ b/server/Makefile-lorax-punica
--- a/server/Makefile-selective-scan
+++ b/server/Makefile-selective-scan
--- a/server/README.md
+++ b/server/README.md
--- a/server/custom_kernels/custom_kernels/fused_attention_cuda.cu
+++ b/server/custom_kernels/custom_kernels/fused_attention_cuda.cu
--- a/server/custom_kernels/custom_kernels/fused_bloom_attention_cuda.cu
+++ b/server/custom_kernels/custom_kernels/fused_bloom_attention_cuda.cu