Commit Graph

42 Commits

Author SHA1 Message Date
Eugene Rakhmatulin
c2fe579ccc Enhance .env file handling and validation in scripts 2026-03-25 23:16:56 -07:00
Eugene Rakhmatulin
8b7c02aa25 add .env support to build-and-copy.sh 2026-03-25 22:47:02 -07:00
Eugene Rakhmatulin
2f5ff0211e Cleanup in build script 2026-03-25 15:39:23 -07:00
Eugene Rakhmatulin
4a0feea6c3 Added --cleanup option to build script 2026-03-25 15:35:32 -07:00
Eugene Rakhmatulin
7fa69187df metadata changes 2026-03-24 22:18:07 -07:00
Drew Botwinick
d6e76f8e2f add build metadata generation and include in Dockerfiles 2026-03-21 16:10:04 -05:00
Alan Pairmont
b879b7748f add network arg to common build flags 2026-03-16 12:09:59 -04:00
Tim Messerschmidt
b9fc32ec34 fix: skip empty lines in wheel download read loop
Add a guard to skip empty lines (e.g. trailing newlines) in the
while-read loop to prevent try_download_wheels from breaking on
unexpected blank input.
2026-03-07 05:06:12 +01:00
Eugene Rakhmatulin
5346372f14 More robust wheels check before download 2026-03-05 17:06:57 -08:00
Eugene Rakhmatulin
2d03bc138d saving flashinfer and vllm commits in wheels directories 2026-03-05 14:41:25 -08:00
Eugene Rakhmatulin
ca34ebcffc Merge branch 'main' into vllm-wheels 2026-03-04 15:59:16 -08:00
Eugene Rakhmatulin
2152ef127d Now can use prebuilt vLLM wheels 2026-03-04 13:33:32 -08:00
Eugene Rakhmatulin
19f06a0d16 Fixed a bug with checking whether we need to download remote wheels 2026-03-04 13:00:40 -08:00
Eugene Rakhmatulin
349a270c1e More robust handling of wheels downloads 2026-02-19 13:47:59 -08:00
Eugene Rakhmatulin
f09c2c3ac8 Refactoring, updated README 2026-02-18 15:58:53 -08:00
Eugene Rakhmatulin
8873a0d959 Handle failed downloads properly 2026-02-18 14:55:43 -08:00
Eugene Rakhmatulin
34fff7b3fb Download flashinfer wheels from releases 2026-02-18 14:46:01 -08:00
Eugene Rakhmatulin
b06531f70b Backup old wheels before rebuilding and restore on failure 2026-02-17 23:13:25 -08:00
Eugene Rakhmatulin
a49b89a0e5 Remove old wheels before rebuilding 2026-02-17 23:04:58 -08:00
Eugene Rakhmatulin
ec0f189256 Initial refactoring to enable separate wheel builds 2026-02-17 19:15:32 -08:00
Eugene Rakhmatulin
4214d4fefe Caching cubins during build for reuse 2026-02-13 19:30:28 -08:00
Eugene Rakhmatulin
3b1e49dcb0 Supporting other CUDA archs via --gpu-arch flag 2026-02-11 13:10:41 -08:00
Eugene Rakhmatulin
ace16f3a8f Applied new fastsafetensors fix to mxfp4 build; disabled wheel builds by default 2026-02-09 23:47:06 -08:00
Eugene Rakhmatulin
06e8817f18 Triton 3.6.0 is now default 2026-02-08 22:38:31 -08:00
Eugene Rakhmatulin
c42cc56d34 bugfix 2026-02-03 14:17:30 -08:00
Eugene Rakhmatulin
d7e9f17c2e vLLM build-time PRs support 2026-02-03 14:14:11 -08:00
Eugene Rakhmatulin
ef0f996df6 Bumped base image version; reverted Triton to 3.5.1 2026-01-29 23:14:43 -08:00
Eugene Rakhmatulin
564afc1f6b Working MXFP4 fork, updated build script 2026-01-26 22:31:46 -08:00
Eugene Rakhmatulin
e817f3dbec Updated Triton version to 3.6.0 2026-01-26 14:24:58 -08:00
Eugene Rakhmatulin
1139a37324 Added transformers v5 support 2025-12-21 22:41:03 -08:00
Eugene Rakhmatulin
11db634aad Switch to uv in the main Dockerfile 2025-12-21 13:28:40 -08:00
Eugene Rakhmatulin
bbd3469549 Support vLLM release wheels 2025-12-21 11:15:52 -08:00
Eugene Rakhmatulin
dfe426e912 Add support for pre-release FlashInfer packages in Docker builds 2025-12-20 23:13:26 -08:00
Eugene Rakhmatulin
76988e0c75 Added --use-wheels to use precompiled vLLM wheels instead of compiling from the source 2025-12-20 20:25:07 -08:00
Eugene Rakhmatulin
a351f182cc Implement autodiscovery for copy hosts and enhance interface detection in build-and-copy and launch-cluster scripts 2025-12-19 10:36:39 -08:00
Eugene Rakhmatulin
23858a3c7f Merge branch 'main' into pr-2 2025-12-19 08:51:52 -08:00
Eugene Rakhmatulin
442f7369ad Updated build script to handle BUILD_JOBS argument 2025-12-18 22:02:04 -08:00
Eric Lewis
11355677f6 Add parallel copy option to build-and-copy.sh
Introduced the --copy-parallel flag to enable concurrent copying of Docker images to multiple hosts. Updated the README with usage instructions and details about the new option. Refactored the script to support both serial and parallel copy modes for improved efficiency.
2025-12-18 01:24:48 -05:00
Eric Lewis
e67abd5e6e Add multi-host copy support to build-and-copy.sh
Updated build-and-copy.sh to support copying Docker images to multiple hosts using the new -c/--copy-to flag, which accepts space- or comma-separated host lists. The old --copy-to-host flag is retained as an alias for backward compatibility, and -h is now used for help. The README was updated to document these changes and provide new usage examples.
2025-12-18 00:32:45 -05:00
Eugene Rakhmatulin
0606b1b984 Refactor Triton and vLLM reference handling in Dockerfile and build script 2025-12-14 23:28:08 -08:00
eugr
e8a12da072 Build triton from source; add TRITON_SHA argument to specify triton release, and add timing statistics 2025-12-14 00:30:50 -08:00
eugr
270446be27 Add build-and-copy script for automated image building and deployment 2025-12-05 11:28:43 -08:00