Skip to content

Pull requests: HabanaAI/vllm-hpu-extension

New pull request New
32 Open 352 Closed
32 Open 352 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

enable calibration for qwen3-vl and glm-4.6
#388 opened Oct 31, 2025 by yangulei Loading…
1
Add dynamic_quant_for_gaudi2.py script to convert model
#387 opened Oct 29, 2025 by wenbinc-Bin Loading…
5
enable dynamic quant of the weights on CPU
#386 opened Oct 29, 2025 by yangulei Loading…
2
add padding ratio limit to the context bucketing
#385 opened Oct 28, 2025 by yangulei Loading…
1
[SW-238300] Disabling dynamic quantization in mlp module
#383 opened Oct 26, 2025 by HolyFalafel Loading…
Enable chunked prefill on aice 1.22
#381 opened Oct 23, 2025 by YuJiankang Loading…
[WA] bypass the GLM OOM issue
#380 opened Oct 15, 2025 by czhu15 Loading…
pass chunk_size and global_num_experts to the MoE kernel
#369 opened Sep 19, 2025 by yangulei Loading…
3
Llama-4 FP8 quantization with expert parallel support
#364 opened Sep 16, 2025 by nazneenn • Draft
Enable chunked prefill
#362 opened Sep 14, 2025 by jzhoulon Loading…
[HS-6944] Fix for deepseek distill models
#359 opened Sep 10, 2025 by nazneenn Loading…
[aice/v.1.22] refactor chunk size code
#354 opened Sep 1, 2025 by ranzhejiang Loading…
3
Fix for Llama4 models (targets main)
#341 opened Aug 19, 2025 by vidyasiv Loading…
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…
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
ProTip! What’s not been updated in a month: updated:<2025-09-30.