Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
Narsil created a review comment on a pull request on huggingface/text-generation-inference
Yes, and serde(renamed) actually modifies what the input is from the user.
Narsil created a review comment on a pull request on huggingface/text-generation-inference
What happens if tool_choice is "required" and no tools are sent ? ("auto", tools = []) we should just ignore the grammar right ?
Narsil created a review comment on a pull request on huggingface/text-generation-inference
Oops
kozistr created a comment on an issue on huggingface/text-generation-inference
> Hi @kozistr @ErikKaum , > > I tested this PR and I can confirm that it works in my case - opentelemetry trace is propagated from request to TGI. > > Thanks again @kozistr ! great to hear...
ErikKaum created a comment on an issue on huggingface/text-generation-inference
Big thanks @kozistr 🙌
Narsil created a review comment on a pull request on huggingface/text-generation-inference
Doesn't a default take care of that ? And shouldn't the default be "auto"?
Narsil created a review comment on a pull request on huggingface/text-generation-inference
> I thought it may be helpful in automatically checking the spec Then let's wait for it to be actually relevant, it's not usually a good thing to do things "because we might need it". Either you...
ptanov created a comment on an issue on huggingface/text-generation-inference
Hi @kozistr @ErikKaum , I tested this PR and I can confirm that it works in my case - opentelemetry trace is propagated from request to TGI. Thanks again @kozistr !
mht-sharma created a comment on a pull request on huggingface/text-generation-inference
Hi @cazlo, thanks for the PR. FYI, you would also need to modify the: [vllm](https://github.com/huggingface/text-generation-inference/blob/main/server/Makefile-vllm#L19) and [flash-attention CK](h...
Narsil created a review comment on a pull request on huggingface/text-generation-inference
Why not `in {torch.float8_e5m2, torch.float8_e4m3}` ?
Narsil pushed 1 commit to feat/prefix_chunking huggingface/text-generation-inference
- Fix env name 812aa1c
Narsil pushed 1 commit to feat/prefix_chunking huggingface/text-generation-inference
- Put back non default simple tests. 52eaa1f
Narsil pushed 1 commit to feat/prefix_chunking huggingface/text-generation-inference
- Add simple resolution when user specifies ATTENTION=paged. ff36b2f
Narsil pushed 1 commit to feat/prefix_chunking huggingface/text-generation-inference
- Fix prefix_caching variable, remove defaults in server (confusing a lot of the times). 5c72f26
OlivierDehaene pushed 1 commit to feat/prefix_chunking huggingface/text-generation-inference
- rename 594a2b4
danieldk pushed 1 commit to main huggingface/text-generation-inference
- Fp8 e4m3_fnuz support for rocm (#2588) * (feat) fp8 fnuz support for rocm * (review comments) Fix compression_con... 704a58c
danieldk closed a pull request on huggingface/text-generation-inference
Fp8 e4m3_fnuz support for rocm
# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, ...danieldk pushed 1 commit to feature/kv-cache-e4m3 huggingface/text-generation-inference
- Support `e4m3fn` KV cache aa92e45