diff qwen3_vl/BUILD @ 275:78699f810817

Add Qwen3-VL and WebRTC dictation services Add Bazel targets for the CUDA-backed Qwen3-VL server and a local WebRTC faster-whisper dictation service. Co-authored-by: Copilot <[email protected]> Copilot-Session: e3d8cb06-6c95-4ae0-9757-651d3796ab00
author MrJuneJune <me@mrjunejune.com>
date Mon, 17 Aug 2026 10:58:47 -0700
parents
children 49e9e591c9bb
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/qwen3_vl/BUILD	Mon Aug 17 10:58:47 2026 -0700
@@ -0,0 +1,66 @@
+load("@rules_shell//shell:sh_binary.bzl", "sh_binary")
+load("@rules_shell//shell:sh_test.bzl", "sh_test")
+load(":runtime.bzl", "cuda_runtime")
+
+cuda_runtime(
+    name = "llama_cpp_cuda_runtime",
+    cuda_runtime = "@llama_cpp_win_cuda_12_4_cudart_x64//:runtime",
+    llama_runtime = "@llama_cpp_win_cuda_12_4_x64//:runtime",
+)
+
+sh_binary(
+    name = "model",
+    srcs = ["qwen3_vl.sh"],
+    args = [
+        "$(rootpath :llama_cpp_cuda_runtime)",
+        "config",
+    ],
+    data = [":llama_cpp_cuda_runtime"],
+)
+
+sh_binary(
+    name = "download_model",
+    srcs = ["qwen3_vl.sh"],
+    args = [
+        "$(rootpath :llama_cpp_cuda_runtime)",
+        "download",
+    ],
+    data = [":llama_cpp_cuda_runtime"],
+)
+
+sh_binary(
+    name = "preflight",
+    srcs = ["qwen3_vl.sh"],
+    args = [
+        "$(rootpath :llama_cpp_cuda_runtime)",
+        "preflight",
+    ],
+    data = [":llama_cpp_cuda_runtime"],
+)
+
+sh_binary(
+    name = "chat",
+    srcs = ["qwen3_vl.sh"],
+    args = [
+        "$(rootpath :llama_cpp_cuda_runtime)",
+        "chat",
+    ],
+    data = [":llama_cpp_cuda_runtime"],
+)
+
+sh_binary(
+    name = "serve",
+    srcs = ["qwen3_vl.sh"],
+    args = [
+        "$(rootpath :llama_cpp_cuda_runtime)",
+        "serve",
+    ],
+    data = [":llama_cpp_cuda_runtime"],
+)
+
+sh_test(
+    name = "qwen3_vl_test",
+    srcs = ["qwen3_vl_test.sh"],
+    data = ["qwen3_vl.sh"],
+    deps = ["@bazel_tools//tools/bash/runfiles"],
+)