Skip to content

Pull requests: HabanaAI/vllm-hpu-extension

New pull request New
30 Open 229 Closed
30 Open 229 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

Introduce block_softmax_adjustment kernel (#163)
#263 opened Jul 8, 2025 by kdamaszk • Draft
[UX] Warning for exponential bucketing
#262 opened Jul 8, 2025 by adobrzyn Loading…
Remove self_attn & lm_head from Mixtral quant config
#261 opened Jul 7, 2025 by tpawlows Loading…
Update of exponential bs warmup mechanism
#258 opened Jul 4, 2025 by iboiko-habana Loading…
Fix ModuleFusedSDPA graph break
#257 opened Jul 4, 2025 by bkowalskiINTEL Loading…
Fix for calibration error TypeError: generate_responses() missing 1 required positional argument: 'args'
#255 opened Jul 2, 2025 by tthakkal Loading…
2
Enable block_softmax_adjustment on Gaudi2
#254 opened Jul 2, 2025 by kdamaszk • Draft
[SW-233526]Fix runtime dequant for block fp8
#251 opened Jul 1, 2025 by xuechendi Loading…
vllm hpu-extension for automatization of long context, prompt
#249 opened Jun 30, 2025 by iboiko-habana Loading…
2
Automatization of long context
#248 opened Jun 30, 2025 by iboiko-habana Loading…
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
Update dependabot.yml
#242 opened Jun 26, 2025 by michalkuligowski Loading…
Update linear.py
#239 opened Jun 25, 2025 by michalkuligowski Loading…
Integrating block_softmax
#238 opened Jun 24, 2025 by ksmusz • Draft
10
Remove double generate
#229 opened Jun 18, 2025 by adobrzyn Loading…
Exponential bucketing tweaks
#224 opened Jun 13, 2025 by madamczyk-intel Loading…
Find bucket with bmin not divs by step
#212 opened Jun 5, 2025 by adobrzyn Loading…
1
Fix max_blocks for warmup decode buckets in case of disabled CONTIGUOUS PA feature
#204 opened May 29, 2025 by iboiko-habana Loading…
1
Use sets for faster filter checks. Better long context support
#203 opened May 28, 2025 by pi314ever Loading…
3
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
fix the issue that bmax not in bucket buffer
#191 opened May 22, 2025 by sywangyi Loading…
4
[SW-233624] Unify FusedMoe with expert parallelism
#175 opened May 14, 2025 by mengniwang95 Loading…
50
Optimized MoE on Gaudi
#159 opened Apr 18, 2025 by gyou2021 • Draft
36
ProTip! Exclude everything labeled bug with -label:bug.