Skip to content

Actions: vllm-project/tpu-inference

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
5,429 workflow runs
5,429 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Publish Package to PyPI Publish Package to PyPI #20: Scheduled
31s main
main
31s
Centralizes environment variable access by routing variables reads through the envs.py module pre-commit #4277: Pull request #1147 synchronize by xingliu14
36s xingliu14:env_var
xingliu14:env_var
36s
Centralizes environment variable access by routing variables reads through the envs.py module pre-commit #4276: Pull request #1147 synchronize by xingliu14
42s xingliu14:env_var
xingliu14:env_var
42s
Centralizes environment variable access by routing variables reads through the envs.py module pre-commit #4275: Pull request #1147 synchronize by xingliu14
39s xingliu14:env_var
xingliu14:env_var
39s
Use Qwen for DP correctness test (#1160) pre-commit #4274: Commit 11d0f33 pushed by kyuyeunk
39s main
main
39s
Use Qwen for DP correctness test pre-commit #4273: Pull request #1160 synchronize by wenxindongwork
5m 47s dp_test_fix
dp_test_fix
5m 47s
Use Qwen for DP correctness test pre-commit #4272: Pull request #1160 opened by wenxindongwork
6m 48s dp_test_fix
dp_test_fix
6m 48s
Use Qwen for DP correctness test Apply Conditional PR Template #1123: Pull request #1160 opened by wenxindongwork
1m 24s dp_test_fix
dp_test_fix
1m 24s
[DP] Functional DP for GPT-OSS (#1137) pre-commit #4271: Commit 587c14f pushed by wenxindongwork
43s main
main
43s
[DP] Functional DP for GPT-OSS pre-commit #4270: Pull request #1137 synchronize by wenxindongwork
42s torch-dp-pr
torch-dp-pr
42s
[FusedMoE] Support sub-channel quantization: FP4, FP8, INT8, ... (#1158) pre-commit #4269: Commit 0ba0c92 pushed by kyuyeunk
39s main
main
39s
[FIX] Add dummy get_input_embeddings to fix vLLM model type check (#971) pre-commit #4268: Commit add0b5b pushed by kyuyeunk
40s main
main
40s
[FIX] Add dummy get_input_embeddings to fix vLLM model type check pre-commit #4267: Pull request #971 synchronize by kuafou
43s kuafou:qi/fix-vllm-model-wrapper
kuafou:qi/fix-vllm-model-wrapper
43s
Publish Package to PyPI Publish Package to PyPI #19: Scheduled
26s main
main
26s
Use FP8_e5m2 automatically when using quantized kv cache FP8 on trill… pre-commit #4266: Commit 4c2a11a pushed by kyuyeunk
46s main
main
46s
[DP] Functional DP for GPT-OSS pre-commit #4265: Pull request #1137 synchronize by wenxindongwork
36s torch-dp-pr
torch-dp-pr
36s
[DP] Functional DP for GPT-OSS pre-commit #4264: Pull request #1137 synchronize by wenxindongwork
41s torch-dp-pr
torch-dp-pr
41s
[FusedMoE] Support sub-channel quantization: FP4, FP8, INT8, ... pre-commit #4263: Pull request #1158 synchronize by bythew3i
42s jevin-kernel
jevin-kernel
42s
[FusedMoE] Support sub-channel quantization: FP4, FP8, INT8, ... pre-commit #4262: Pull request #1158 synchronize by bythew3i
42s jevin-kernel
jevin-kernel
42s
[FusedMoE] Support sub-channel quantization: FP4, FP8, INT8, ... pre-commit #4261: Pull request #1158 synchronize by bythew3i
35s jevin-kernel
jevin-kernel
35s
[FusedMoE] Support sub-channel quantization: FP4, FP8, INT8, ... pre-commit #4260: Pull request #1158 opened by bythew3i
38s jevin-kernel
jevin-kernel
38s
[FusedMoE] Support sub-channel quantization: FP4, FP8, INT8, ... Apply Conditional PR Template #1122: Pull request #1158 opened by bythew3i
19s jevin-kernel
jevin-kernel
19s
Publish Package to PyPI Publish Package to PyPI #18: Scheduled
37s main
main
37s
Fix numerical issue on hybrid kv cache allocation (#1139) pre-commit #4259: Commit cfc7610 pushed by Chenyaaang
46s main
main
46s
[TPU Offload] Separate offload manager and cpu-cache backend, and code structure refactor pre-commit #4258: Pull request #1122 synchronize by juncgu-google
33s cpu-offloading/dev-cpu-backend
cpu-offloading/dev-cpu-backend
33s