Skip to content

Pull requests: ROCm/vllm

New pull request New
29 Open 378 Closed
29 Open 378 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Quant] [Feature] Per-Token-Activation Per-Channel-Weight FP8 Quantization
#412 opened Feb 7, 2025 by tjtanaa Loading…
Optimization for quantized gemm skinny sizes
#411 opened Feb 7, 2025 by amd-hhashemi Loading…
Using 6.3.2 ROCm image as base
#410 opened Feb 6, 2025 by gshtras Loading…
K8test baseline -> Testing a single MI300 8x GPU node for CI performance // no need to merge
#409 opened Feb 6, 2025 by Alexei-V-Ivanov-AMD Loading…
Add VLLM_USE_AITER as docker build arg
#408 opened Feb 6, 2025 by arakowsk-amd Loading…
K8 node testing // no need to merge
#404 opened Feb 4, 2025 by Alexei-V-Ivanov-AMD Loading…
Add tuned moe config for qwen1.5_moe_A2.7B
#398 opened Feb 3, 2025 by sky0530 Loading…
4
Fp8 header
#396 opened Jan 31, 2025 by gshtras Loading…
Test queue with 8 gpu
#393 opened Jan 29, 2025 by dhonnappa-amd Loading…
[Bugfix] Deepseek v3 fix max_num_batched_tokens
#386 opened Jan 24, 2025 by Concurrensee • Draft
[Feature] Faster Custom Paged Attention kernels
#385 opened Jan 24, 2025 by tjtanaa • Draft
Switching building to MI300.
#380 opened Jan 22, 2025 by Alexei-V-Ivanov-AMD Loading…
Adding Deepseek instruct + update manifest
#379 opened Jan 22, 2025 by arakowsk-amd Loading…
Add TritonScaledMMLinearKernel to fix broken support for int8 models
#377 opened Jan 21, 2025 by rasmith Loading…
Trying to pass toml file as a parameter to codespell
#376 opened Jan 21, 2025 by gshtras Loading…
Fixing home dirs. // Testing internal CI.
#371 opened Jan 21, 2025 by Alexei-V-Ivanov-AMD Loading…
merge paged attention feature and moe feature into llama_fp8_12062024
#370 opened Jan 21, 2025 by yuzho-amd • Draft
[Minor] Hip cmake passthrough
#362 opened Jan 15, 2025 by tvirolai-amd Loading…
1
[Cleanup] Remove obsolete patches and references and test CI
#354 opened Jan 9, 2025 by hongxiayang Loading…
add video group for test user
#348 opened Jan 6, 2025 by dhonnappa-amd Loading…
[Minor] updating Docker manifest
#334 opened Dec 18, 2024 by arakowsk-amd Loading…
Merging PR#327 into main branch
#328 opened Dec 13, 2024 by pramenku Loading…
1
dummy commit to trigger buildkite job
#311 opened Dec 7, 2024 by dhonnappa-amd Loading…
Enable CK Attention for Navi31
#285 opened Nov 18, 2024 by hyoon1 Loading…
4
Add vectorized rms_norm support for Navi31
#273 opened Nov 12, 2024 by hyoon1 Loading…
3
ProTip! What’s not been updated in a month: updated:<2025-01-09.