EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CI][lint] Add rule codespell back (#6236)

Browse Source 
### What this PR does / why we need it?
After removing codepsell a while, we discovered that typo had a problem
correctly recognizing certain misspelled words, so I suggested adding it
back.

- vLLM version: v0.14.1
- vLLM main:
d68209402d

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2026-01-26 14:12:33 +08:00
committed by GitHub
parent f4abd9b7b5
commit c26ad78f86
33 changed files with 67 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/developer_guide/feature_guide/context_parallel.md
View File

@@ -38,7 +38,7 @@ Given that PCP and DCP behave similarly for KV cache sharding, we refer to them
As illustrated, a virtual block is defined in the block table, where blocks within the same CP device group form a virtual block. The virtual block size is `virtual_block_size = block_size * cp_size`.
For any token `x`, referencing the folloing figure, its (virtual) block index is `x // virtual_block_size`, and the offset within the virtual block is `offset_within_virtual_block = x % virtual_block_size`.
For any token `x`, referencing the following figure, its (virtual) block index is `x // virtual_block_size`, and the offset within the virtual block is `offset_within_virtual_block = x % virtual_block_size`.
The local block index is `local_block_index = offset_within_virtual_block // cp_kv_cache_interleave_size`, and the device number is `target_rank = local_block_index % cp_size`.
The offset within the local block is `(local_block_index // cp_size) * cp_kv_cache_interleave_size + offset_within_virtual_block % cp_kv_cache_interleave_size`.

2
docs/source/tutorials/DeepSeek-V3.1.md
View File

@@ -699,7 +699,7 @@ The performance result is:
**Input/Output**: 3.5k/1.5k
**Performance**: TTFT = 6.16s, TPOT = 48.82ms, Average performance of each card is 478 TPS (Token Per Secon).
**Performance**: TTFT = 6.16s, TPOT = 48.82ms, Average performance of each card is 478 TPS (Token Per Second).
### Using vLLM Benchmark

4
docs/source/user_guide/release_notes.md
View File

@@ -2,7 +2,7 @@
## v0.13.0rc2 - 2026.01.24
This is the second release candidate of v0.13.0 for vLLM Ascend. In this rc relesae, we fixed lots of bugs and improved the performance of many models. Please follow the [official doc](https://docs.vllm.ai/projects/ascend/en/v0.13.0/) to get started. Any feedback is welcome to help us to improve the final version of v0.13.0.
This is the second release candidate of v0.13.0 for vLLM Ascend. In this rc release, we fixed lots of bugs and improved the performance of many models. Please follow the [official doc](https://docs.vllm.ai/projects/ascend/en/v0.13.0/) to get started. Any feedback is welcome to help us to improve the final version of v0.13.0.
### Highlights
@@ -19,7 +19,7 @@ We mainly focus on quality and performance improvement in this release. The spec
### Model Support
- LongCat-Flash is supproted now.[#3833](https://github.com/vllm-project/vllm-ascend/pull/3833)
- LongCat-Flash is supported now.[#3833](https://github.com/vllm-project/vllm-ascend/pull/3833)
- minimax_m2 is supported now. [#5624](https://github.com/vllm-project/vllm-ascend/pull/5624)
- Support for cross-attention and whisper models [#5592](https://github.com/vllm-project/vllm-ascend/pull/5592)