Brayden Zhong comments

Results 46 comments of


                                            Brayden Zhong

[Feature] Generation Inputs: input_embeds

In https://github.com/sgl-project/sglang/pull/2052

Broken - I'm working on it.

Hey cc @timburgan - any update? :)

ollama doesn't distribute notice licenses in its release artifacts

Bump

[Misc] Benchmarks: Fix guided decoding, token sampling, and request sorting

@aarnphm I agree not related to structured outputs :) If you have the bandwidth, do you mind taking a look?

fix(sdk/cli): Correct HuggingFace model copy

Maybe also cc @aarnphm 👍 thx in advance

fix(sdk/cli): Correct HuggingFace model copy

Sure no problem, I made a new PR for the docs I'll give the example in a sec

[py-tx] Implementation of IVF faiss indices in PDQ

Didn't forget ab this.. I'll check it out tn; thanks for the review!

[py-tx] Implementation of IVF faiss indices in PDQ

Think it's ready to get a second look now?

[py-tx] Implementation of IVF faiss indices in PDQ

> Let me know if you'd rather take a look at these in a followup instead. I think I would prefer that :)

[py-tx] Implementation of IVF faiss indices in PDQ

Ignore the earlier comment: I think I was doing something dumb. ``` python3 benchmarks/benchmark_pdq_indices.py --dataset-size 10000 --num-queries 1000 --implementations index2_flat flat_hash multi_hash --thresholds 31 --query-mode both Benchmark: PDQ Index Implementation...