- From: Kostiainen, Anssi <anssi.kostiainen@intel.com>
- Date: Fri, 24 May 2024 13:22:04 +0000
- To: "public-webmachinelearning-wg@w3.org" <public-webmachinelearning-wg@w3.org>
- Message-ID: <939800BF-02E5-47A2-98E4-C85A8A4BC0AC@intel.com>
Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md
WebML WG Teleconference – 30 May 2024 - 14:00-15:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#webml-wg-teleconference--30-may-2024---1400-1500-utc>
See the timezone table ...
Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#logistics>
* Chair: Anssi
* Scribe: ? (see howto<https://github.com/webmachinelearning/meetings/blob/main/scribe-howto.md>, volunteers welcome!)
* IRC: irc://irc.w3.org:6667/#webmachinelearning
* IRC web client: https://irc.w3.org/?channels=#webmachinelearning
* Joining instructions: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2023Jun/0000.html
* Minutes: https://www.w3.org/2024/05/30-webmachinelearning-minutes.html
Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#agenda>
ℹ️ Announcements
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%E2%84%B9%EF%B8%8F-announcements>
* 🆕 WebNN Developer Preview https://microsoft.github.io/webnn-developer-preview/
* 🆕 Awesome WebNN https://github.com/webmachinelearning/awesome-webnn
* 🆕 TPAC 2024 F2F #23<https://github.com/webmachinelearning/meetings/issues/23>
ℹ️ NPU support
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%E2%84%B9%EF%B8%8F-npu-support>
📌 We agreed to start formalize the NPU support with the simplest design (option 1: deviceType: "npu") informed by implementation experience. Review a draft PR if available, discuss any new information and considerations brought to the group's attention in the issue.
* ⨀ WebNN should support NPU and QDQ operations webmachinelearning/webnn#623<https://github.com/webmachinelearning/webnn/issues/623>
* ⛭ Chromium implementation (NPU device type) https://chromium-review.googlesource.com/c/chromium/src/+/5330647
ℹ️ MLBuffer
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%E2%84%B9%EF%B8%8F-mlbuffer>
📌 Introduce and discuss the direct buffer sharing proposal. Discuss the latest on the device-based storage object. Discuss any other MLBuffer business.
* ⨀ webmachinelearning/webnn#688<https://github.com/webmachinelearning/webnn/issues/688>
* ⨀ webmachinelearning/webnn#542<https://github.com/webmachinelearning/webnn/issues/542>
* 🏷️ All webgpu interop<https://github.com/webmachinelearning/webnn/labels/webgpu%20interop> issues
ℹ️ TAG feedback: threading approach on a GPU
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%E2%84%B9%EF%B8%8F-tag-feedback-threading-approach-on-a-gpu>
TAG is generally happy. One question has arrived regarding threading approach on a GPU. Discuss & formulate the group's response to close on the review.
* ⨀ w3ctag/design-reviews#933 (comment)<https://github.com/w3ctag/design-reviews/issues/933#issuecomment-2126805061>
ℹ️ Open issues and PRs
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%E2%84%B9%EF%B8%8F-open-issues-and-prs>
Discuss open issues and review PRs based on your feedback:
* ⨀ All open issues<https://github.com/webmachinelearning/webnn/issues>
* ⛙ All open pull requests<https://github.com/webmachinelearning/webnn/pulls>
A curated shortlist of recently discussed issues below. If any are addressed prior to the meeting, we'll debrief the group on the changes to keep everyone up to date with significant developments. Please refer to the triage guidance<https://github.com/webmachinelearning/webnn/blob/main/docs/IssueTriage.md> for more on our triage practices.
🏷️ Debrief on PRs merged recently
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%EF%B8%8F-debrief-on-prs-merged-recently>
The editors and PR authors will debrief the group on substantive PRs that got merged in the last few weeks, answer question from the group.
* ⛙ Recently merged PRs<https://github.com/webmachinelearning/webnn/pulls?q=is%3Apr+is%3Amerged>
🏷️ interop<https://github.com/webmachinelearning/webnn/labels/interop>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%EF%B8%8F-interop>
We have a new interop workstream, we'll exercise it. 💪
Discussion on how the group wants to approach the interop issues arising from differences between backends in the most effective manner.
* 🆕 All interop<https://github.com/webmachinelearning/webnn/labels/interop> issues
🏷️ bug<https://github.com/webmachinelearning/webnn/labels/bug>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%EF%B8%8F-bug>
* 🆕 Divide-by-zero outcome should be standardized
* ⨀ webmachinelearning/webnn#691<https://github.com/webmachinelearning/webnn/issues/691>
* ☰ Discuss the proposal to standardize divide-by-zero outcome
* ArgMax/Min selectLastIndex is not supported on CoreML
* ⨀ webmachinelearning/webnn#652<https://github.com/webmachinelearning/webnn/issues/652>
* ☰ Proposal to remove selectLastIndex param, last call to remove
* Consider changing output type of ArgMax/Argmin to int32, or allow passing output_type
* ⨀ webmachinelearning/webnn#653<https://github.com/webmachinelearning/webnn/issues/653>
* ☰ Check if we have new information on int64 examples to unblock the exploration
🏷️ operator specific<https://github.com/webmachinelearning/webnn/labels/operator%20specific>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%EF%B8%8F-operator-specific>
* 🆕 Consider removing lstm and gru operators
* ⨀ webmachinelearning/webnn#689<https://github.com/webmachinelearning/webnn/issues/689>
* ☰ Discuss the proposal and presented options: 1) remove 2) keep 3) water down
🏷️ question<https://github.com/webmachinelearning/webnn/labels/question>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%EF%B8%8F-question>
* Make MLOperandDescriptor.dimensions a FrozenArray
* ⨀ webmachinelearning/webnn#670<https://github.com/webmachinelearning/webnn/issues/670>
* ☰ Discussion on frozen array type subtleties
* Reconsider MLOperand methods
* ⨀ webmachinelearning/webnn#666<https://github.com/webmachinelearning/webnn/issues/666>
* ☰ Review 4 options proposed for the MLOperand methods
* Do we need an MLConstantOperand?
* ⨀ webmachinelearning/webnn#668<https://github.com/webmachinelearning/webnn/issues/668>
* ☰ Revisit with new information from XNNPACK
🏷️ feature request<https://github.com/webmachinelearning/webnn/labels/feature%20request>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-05-30-wg-agenda.md#%EF%B8%8F-feature-request>
* Bitwise operators and logical operators / rename "not" to "logicalNot"
* ⨀ webmachinelearning/webnn#496<https://github.com/webmachinelearning/webnn/issues/496>
* ⛙ (Related) webmachinelearning/webnn#692<https://github.com/webmachinelearning/webnn/pull/692>
* ☰ Review the rename "not" to "logicalNot" PR
* Type casting + MLNumber
* ⨀ Scalar values webmachinelearning/webnn#678<https://github.com/webmachinelearning/webnn/issues/678>
* ⨀ fp64 -> fp32/fp16 webmachinelearning/webnn#325<https://github.com/webmachinelearning/webnn/issues/325>
* ⨀ MLNumber webmachinelearning/webnn#442<https://github.com/webmachinelearning/webnn/issues/442>
* ⛙ webmachinelearning/webnn#647<https://github.com/webmachinelearning/webnn/pull/647>
* ☰ Review (draft) PR, discuss if needed to make progress
* Allow checking whether operators/types are supported for a backend before creating a graph
* ⨀ webmachinelearning/webnn#463<https://github.com/webmachinelearning/webnn/issues/463>
* ☰ Discuss new information from related uint64/int64 data type #654 and MLConstantOperand #668 issues
* Rename MLOperandDescriptor's dimensions to shape
* ⨀ webmachinelearning/webnn#669<https://github.com/webmachinelearning/webnn/issues/669>
* ⛙ webmachinelearning/webnn#676<https://github.com/webmachinelearning/webnn/pull/676>
* ☰ Review (draft) PR as appropriate
* Consider adding node labels for more diagnosable error messages for async errors
* ⨀ webmachinelearning/webnn#585<https://github.com/webmachinelearning/webnn/issues/585>
* ☰ Review alternatives A) add to options dict B) extend MLOperand's label field C) keep current
Received on Friday, 24 May 2024 13:22:19 UTC