Improve docs #17
Merged
Improve docs #17
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
5 tasks
timethink
pushed a commit
to timethink/sglang
that referenced
this pull request
Mar 9, 2025
chunyuan-w
pushed a commit
to chunyuan-w/sglang
that referenced
this pull request
Mar 24, 2025
* Use rms norm kernel instead of vllm * update
pi314ever
pushed a commit
to pi314ever/sglang
that referenced
this pull request
Apr 23, 2025
5 tasks
chunyuan-w
pushed a commit
to chunyuan-w/sglang
that referenced
this pull request
May 28, 2025
* Use rms norm kernel instead of vllm * update
yanbing-j
added a commit
to yanbing-j/sglang
that referenced
this pull request
Jun 3, 2025
* Use rms norm kernel instead of vllm * update
yanbing-j
added a commit
to yanbing-j/sglang
that referenced
this pull request
Jun 4, 2025
* Use rms norm kernel instead of vllm * update
yanbing-j
added a commit
to yanbing-j/sglang
that referenced
this pull request
Jun 10, 2025
* Use rms norm kernel instead of vllm * update
yanbing-j
added a commit
to yanbing-j/sglang
that referenced
this pull request
Jun 18, 2025
* Use rms norm kernel instead of vllm * update
pengxin99
pushed a commit
to pengxin99/sglang
that referenced
this pull request
Jun 19, 2025
5 tasks
yichiche
pushed a commit
to yichiche/sglang
that referenced
this pull request
Jul 30, 2025
* fix decode Signed-off-by: Ivan Butygin <[email protected]> * fix Signed-off-by: Ivan Butygin <[email protected]> --------- Signed-off-by: Ivan Butygin <[email protected]>
yichiche
pushed a commit
to yichiche/sglang
that referenced
this pull request
Aug 7, 2025
* fix decode Signed-off-by: Ivan Butygin <[email protected]> * fix Signed-off-by: Ivan Butygin <[email protected]> --------- Signed-off-by: Ivan Butygin <[email protected]>
yichiche
pushed a commit
to yichiche/sglang
that referenced
this pull request
Aug 11, 2025
* fix decode Signed-off-by: Ivan Butygin <[email protected]> * fix Signed-off-by: Ivan Butygin <[email protected]> --------- Signed-off-by: Ivan Butygin <[email protected]>
5 tasks
5 tasks
JustinTong0323
added a commit
that referenced
this pull request
Oct 30, 2025
* Fix dtype mismatch in rotary embedding with FP8 KV cache When using FP8 KV cache quantization (e.g., with ModelOpt FP8 models), the query and key tensors may have different dtypes during CUDA graph capture. The query tensor remains in bfloat16 for computation, while the key tensor might need to be in FP8 format for KV cache storage. The issue was in DeepseekScalingRotaryEmbedding.forward_native() which only captured query's dtype and then converted both query and key to that same dtype. This caused a dtype mismatch error during CUDA graph capture: "query and key must have the same dtype". The fix preserves the original dtypes of both query and key tensors separately, ensuring they maintain their intended dtypes after the rotary position embedding computation. This resolves the CUDA graph capture failure with Qwen3MoE and other models using FP8 KV cache quantization. * Fix FA4 dtype mismatch with FP8 KV cache When using FlashAttention 4 (FA4) with FP8 KV cache quantization, there was a dtype mismatch between the query tensor (bfloat16) and the cached key/value tensors (FP8). FA4 requires all input tensors (q, k, v) to have the same dtype. The previous code only converted the query to FP8 when NOT using FA4 (fa_impl_ver != 4). This was based on the assumption that FA4 doesn't support FP8, but actually FA4 CAN work with FP8 tensors as long as all tensors have matching dtypes. The key difference is that FA4 doesn't support descale parameters for on-the-fly dequantization (unlike FA3). So we: 1. Convert query to FP8 to match the KV cache dtype for both FA3 and FA4 2. Only set k_descale/v_descale for FA3 (FA4 doesn't support them) This resolves the "query and key must have the same dtype" error when using FP8 KV cache with FA4. --------- Co-authored-by: Cursor Agent <[email protected]>
JustinTong0323
added a commit
that referenced
this pull request
Oct 30, 2025
This reverts commit fc80fbd.
key4ng
pushed a commit
to key4ng/sglang
that referenced
this pull request
Nov 9, 2025
5 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.