Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
79 Open 1,202 Closed
79 Open 1,202 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

Port: Update readme with exponential warmup as default
#1366 opened Jun 4, 2025 by iboiko-habana Loading…
1
Fix OOM in fp8 w/ HPUGraph for llama3.2
#1365 opened Jun 4, 2025 by zhouyu5 • Draft
Add PP support for Prefill/Decode Disaggregation
#1364 opened Jun 4, 2025 by lvliang-intel Loading…
changes to enable LMCache v1 baseline
#1361 opened Jun 3, 2025 by hsubramony Loading…
Set simple_compile_backend for HpuPlatform
#1359 opened Jun 3, 2025 by Kacper-Pietkun Loading…
3
[SW-229465] Search for multiple RoPE modules
#1355 opened Jun 3, 2025 by RafLit Loading…
Adjust batch size to match bucket size
#1354 opened Jun 3, 2025 by xhaihao Loading…
Remove duplicate kv_b_proj from models using MLA
#1349 opened Jun 2, 2025 by kwisniewski98 Loading…
13
by default disable contiguous_pa on Gaudi2.
#1345 opened May 30, 2025 by ccrhx4 Loading…
7
[WIP] Enable interleaved sliding_window for gemma3
#1344 opened May 30, 2025 by jiminha • Draft
[draft] merged_prefill for V1
#1342 opened May 29, 2025 by madamczyk-intel • Draft
5
[WIP][TC][FP8] Enable dynamo to create floating point data-dependent fxgraphs
#1340 opened May 29, 2025 by jczaja Loading…
Revise DeepSeek-R1 README and update start scripts
#1339 opened May 29, 2025 by taotod Loading…
1
[deepseek_r1] Enable StaticMoE for decoding phase of static activation quant path
#1338 opened May 29, 2025 by yangulei Loading…
1
fix requirements/hpu.txt for hpu extension
#1336 opened May 29, 2025 by ranzhejiang Loading…
Fix prefill warm up issue
#1335 opened May 29, 2025 by yeonsily • Draft
[V1] Add new block scheduling queue to select blocks with lowest id
#1329 opened May 28, 2025 by jkaniecki Loading…
1
Fix vllm crash when running with lm-eval
#1321 opened May 27, 2025 by ccrhx4 Loading…
3
Add Flag to speed up Qwen3 fp8 warmup issue
#1319 opened May 27, 2025 by Yanli2190 Loading…
7
[Gaudi][Intel] Update Dockerfile.hpu for Gaudi 1.20.1
#1316 opened May 26, 2025 by vinayK34 Loading…
1
[draft] Optimize RotaryEmbedding for reuse in t.compile with dynamic shapes
#1315 opened May 26, 2025 by anko-intel Loading…
3
[Torch compile] Torch compilation on Sampler
#1314 opened May 26, 2025 by jczaja Loading…
Enabled MoE for both BF16 and INC based FP8 on Gaudi
#1309 opened May 23, 2025 by gyou2021 Loading…
4
parallel compile for fast warm up
#1304 opened May 22, 2025 by inkcherry Loading…
optimize transfer time. use mooncake put/get_unsafe.
#1297 opened May 22, 2025 by jikunshang Loading…
ProTip! Updated in the last three days: updated:>2025-06-01.