Skip to content

Actions: vllm-project/vllm

Lint and Deploy Charts

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
5,251 workflow runs
5,251 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[V1][Misc] Shorten FinishReason enum and use constant strings
Lint and Deploy Charts #5252: Pull request #12760 opened by njhill
February 5, 2025 02:46 6m 53s njhill:finish-reason
February 5, 2025 02:46 6m 53s
[build][misc] allow to use recent numpy
Lint and Deploy Charts #5251: Pull request #12759 opened by zhouyuan
February 5, 2025 02:43 6m 52s zhouyuan:wip_numpy_bump
February 5, 2025 02:43 6m 52s
[Misc] Update w2 scale loading for GTPQMarlinMoE
Lint and Deploy Charts #5250: Pull request #12757 opened by dsikka
February 5, 2025 02:36 7m 25s neuralmagic:fix_gptq_marlin_condition
February 5, 2025 02:36 7m 25s
[Model][Speculative Decoding] DeepSeek MTP spec decode
Lint and Deploy Charts #5249: Pull request #12755 synchronize by luccafong
February 5, 2025 02:30 6m 57s luccafong:ds_mtp
February 5, 2025 02:30 6m 57s
[Model][Speculative Decoding] DeepSeek MTP spec decode
Lint and Deploy Charts #5248: Pull request #12755 synchronize by luccafong
February 5, 2025 02:22 7m 15s luccafong:ds_mtp
February 5, 2025 02:22 7m 15s
[Model][Speculative Decoding] DeepSeek MTP spec decode
Lint and Deploy Charts #5247: Pull request #12755 synchronize by luccafong
February 5, 2025 02:20 7m 34s luccafong:ds_mtp
February 5, 2025 02:20 7m 34s
[Model][Speculative Decoding] DeepSeek MTP spec decode
Lint and Deploy Charts #5246: Pull request #12755 synchronize by luccafong
February 5, 2025 02:13 6m 46s luccafong:ds_mtp
February 5, 2025 02:13 6m 46s
[MISC] add arg pad_for_invariant_seq_len
Lint and Deploy Charts #5245: Pull request #12397 synchronize by MengqingCao
February 5, 2025 02:03 7m 45s MengqingCao:fix
February 5, 2025 02:03 7m 45s
[Distributed][refactor] Add base class for device-specific communicator
Lint and Deploy Charts #5244: Pull request #11324 synchronize by MengqingCao
February 5, 2025 01:56 6m 53s MengqingCao:communicator
February 5, 2025 01:56 6m 53s
[V1][Metrics] Add GPU prefix cache hit rate % gauge
Lint and Deploy Charts #5243: Pull request #12592 synchronize by comaniac
February 5, 2025 01:15 6m 57s comaniac:v1-cache-metric-2
February 5, 2025 01:15 6m 57s
[Model][Speculative Decoding] DeepSeek MTP spec decode
Lint and Deploy Charts #5242: Pull request #12755 synchronize by luccafong
February 5, 2025 00:27 6m 58s luccafong:ds_mtp
February 5, 2025 00:27 6m 58s
[V1] PR 1/N for v1 sample and prompt logprobs support
Lint and Deploy Charts #5241: Pull request #9880 synchronize by njhill
February 5, 2025 00:26 6m 45s neuralmagic:afeldman-nm/v1_logprobs
February 5, 2025 00:26 6m 45s
[Model][Speculative Decoding] DeepSeek MTP spec decode
Lint and Deploy Charts #5240: Pull request #12755 synchronize by luccafong
February 5, 2025 00:06 7m 1s luccafong:ds_mtp
February 5, 2025 00:06 7m 1s
[Model][Speculative Decoding] DeepSeek MTP spec decode
Lint and Deploy Charts #5239: Pull request #12755 opened by luccafong
February 4, 2025 23:58 7m 28s luccafong:ds_mtp
February 4, 2025 23:58 7m 28s
Expert Parallelism (EP) Support for DeepSeek V2
Lint and Deploy Charts #5238: Pull request #12583 synchronize by cakeng
February 4, 2025 23:22 7m 7s cakeng:moe
February 4, 2025 23:22 7m 7s
[V1] PR 1/N for v1 sample and prompt logprobs support
Lint and Deploy Charts #5236: Pull request #9880 synchronize by njhill
February 4, 2025 22:59 7m 13s neuralmagic:afeldman-nm/v1_logprobs
February 4, 2025 22:59 7m 13s
[Frontend] Generate valid tool call IDs when using tokenizer-mode=mistral
Lint and Deploy Charts #5234: Pull request #12332 synchronize by rafvasq
February 4, 2025 22:24 7m 24s rafvasq:fix-mistral-tool-call
February 4, 2025 22:24 7m 24s
[Frontend] Generate valid tool call IDs when using tokenizer-mode=mistral
Lint and Deploy Charts #5233: Pull request #12332 synchronize by rafvasq
February 4, 2025 22:21 10m 47s rafvasq:fix-mistral-tool-call
February 4, 2025 22:21 10m 47s
[Frontend] Generate valid tool call IDs when using tokenizer-mode=mistral
Lint and Deploy Charts #5232: Pull request #12332 synchronize by rafvasq
February 4, 2025 22:20 11m 1s rafvasq:fix-mistral-tool-call
February 4, 2025 22:20 11m 1s
[Frontend] Generate valid tool call IDs when using tokenizer-mode=mistral
Lint and Deploy Charts #5231: Pull request #12332 synchronize by rafvasq
February 4, 2025 22:16 12m 0s rafvasq:fix-mistral-tool-call
February 4, 2025 22:16 12m 0s
vllm-flash-attn build on AMD
Lint and Deploy Charts #5230: Pull request #12566 synchronize by ProExpertProg
February 4, 2025 21:52 7m 0s neuralmagic:luka/amd-rocm-vllm-fa
February 4, 2025 21:52 7m 0s
Fix OpenVINO device
Lint and Deploy Charts #5229: Pull request #12750 opened by hmellor
February 4, 2025 21:39 6m 59s hmellor:fix-openvino
February 4, 2025 21:39 6m 59s
[WIP][Attention] WIP MLA with chunked prefill
Lint and Deploy Charts #5228: Pull request #12639 synchronize by LucasWilkinson
February 4, 2025 21:15 6m 59s LucasWilkinson:lwilkinson/chunked-mla
February 4, 2025 21:15 6m 59s