Skip to content

Pull requests: HabanaAI/vllm-hpu-extension

New pull request New
27 Open 318 Closed
27 Open 318 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[SW-235186] Enable group indexing support
#349 opened Aug 25, 2025 by jmamzax Loading…
Fix the warmup issue of batch expansion for Deepseek MTP
#343 opened Aug 21, 2025 by YuJiankang Loading…
1
Modify ops.py for hunyuan fp8 model implementation
#342 opened Aug 20, 2025 by tianyuan211 Loading…
3
Fix for Llama4 models (targets main)
#341 opened Aug 19, 2025 by vidyasiv Loading…
Pass Attn Sinks to Fused SDPA
#339 opened Aug 18, 2025 by SKRohit Loading…
[SW-227615] adding quant config files to vllm
#336 opened Aug 14, 2025 by linoybu Loading…
1
Fix for Llama4 models
#329 opened Aug 11, 2025 by vidyasiv Loading…
2 tasks done
Add support for block_softmax_const_max
#327 opened Aug 7, 2025 by mswiniarsk • Draft
Add flag pin_memory to call from hpu.py in vllm
#325 opened Aug 5, 2025 by xuechendi Loading…
1
Add Calibration Script for SGLang FP8
#318 opened Jul 29, 2025 by SKRohit Loading…
1
Fix the fusedsdpa with sliding window alignment issue
#298 opened Jul 17, 2025 by libinta Loading…
2
Draft: Proper chunked prefill bucketing
#295 opened Jul 16, 2025 by kzawora-intel • Draft
6
Add block_softmax_adjustment and block_softmax kernels
#289 opened Jul 16, 2025 by czhu15 Loading…
Enable calibration using pile-10k dataset for DeepSeek models
#279 opened Jul 14, 2025 by yangulei Loading…
1
Introduce block_softmax_adjustment kernel (#163)
#263 opened Jul 8, 2025 by kdamaszk • Draft
Enable block_softmax_adjustment on Gaudi2
#254 opened Jul 2, 2025 by kdamaszk • Draft
Add pre-commit static checks
#247 opened Jun 30, 2025 by kzawora-intel Loading…
Allow usage of fused_block_softmax_adjustment for Qwen with Lazy
#246 opened Jun 27, 2025 by mswiniarsk • Draft
Exponential bucketing tweaks
#224 opened Jun 13, 2025 by madamczyk-intel Loading…
Add useful internal vllm test
#200 opened May 27, 2025 by nirda7 • Draft
4
[SW-225565] Enable triangular softmax with merged prefill
#197 opened May 26, 2025 by kamil-kaczor • Draft
2
Optimized MoE on Gaudi
#159 opened Apr 18, 2025 by gyou2021 • Draft
36
[FIX] fp8 gc compile error
#110 opened Mar 4, 2025 by maktukmak • Draft
1
Expand capability checks
#89 opened Feb 3, 2025 by kzawora-intel • Draft
9
Add renormalize parameter for FusedMOE's & modify experts_max arg of mixture_of_experts()
#70 opened Jan 9, 2025 by tangleintel • Draft
4
ProTip! Type g i on any issue or pull request to go back to the issue listing page.