12月1月2月3月4月5月6月7月8月9月10月11月
周一周三周五
一年内 264266 次贡献
更少更多
- frostbyte_neo 推送了仓库 github-featured/vllm-project--vllm 的 bz/bridge-rust-tool-parser-to-py 分支比较 10 提交 »76c973e13c refactor & simplify53275a22d6 bridge rust tool parser to python9729e05917 fix minimax m3 tool parser rust unit testbe37de73a9 Python ame tool/reasoning parser (#9)e633514f50 [ROCm] minimax-m3 initial enablement on ROCm (#25)
- frostbyte_neo 推送了仓库 github-featured/vllm-project--vllm 的 bz/attractive-termite 分支比较 4 提交 »b6db7065e6 minor refactora2bedb84b6 do not take &&, better error categorization21d8aa7ecc simplify4288f3d3a5 extract chat-renderer crate
- frostbyte_neo 推送了仓库 github-featured/vllm-project--vllm 的 bump_numba 分支比较 2 提交 »607615b7cd pre commit, typo fix5daeb8f6ef Upgrade Numba to fix segfault on CUDA drivers version 580
- frostbyte_neo 推送了仓库 github-featured/vllm-project--vllm 的 builder-nvcc-toolchain 分支比较 2 提交 »c7b1080a64 [Build] Download CUDA 12.9 nvcc/ptxas/cicc for better codegen in Docker build7ed39716c2 [Build] Downgrade default CUDA version to 12.8 for PyTorch cu128 compatibility
- frostbyte_neo 推送了仓库 github-featured/vllm-project--vllm 的 builder-cuda-version 分支比较 3 提交 »9df42d2000 [Build] Update pre-commit pip-compile hook to use cu128 torch backend8d151aa148 [Build] Recompile test.txt lockfile with cu128 torch backend11a13b0fd3 [Docker] Add BUILDER_CUDA_VERSION to decouple build and runtime CUDA versions
- frostbyte_neo 推送了仓库 github-featured/vllm-project--vllm 的 bind_kv_caches 分支bfff9bcd1d [V1] TPU - Remove self.kv_caches
- frostbyte_neo 推送了仓库 github-featured/vllm-project--vllm 的 benchmark_serving_test 分支221118dc85 [Bugfix] Use a different prompt for benchmark_serving.py test prompt
- frostbyte_neo 推送了仓库 github-featured/vllm-project--vllm 的 batched_triton_fallback 分支53fa4c6ad2 Disabled DeepGEMM -> batched triton fallback by default