(tvm) branch main updated: [Web] Fix progress reporting when loading from cache (#18450)

[tqchen]

This is an automated email from the ASF dual-hosted git repository.

tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git


The following commit(s) were added to refs/heads/main by this push:
     new 5d8c4d2727 [Web] Fix progress reporting when loading from cache 
(#18450)
5d8c4d2727 is described below

commit 5d8c4d2727fe678108ceaea48dd6ee35b2317fcf
Author: Mihail Yonchev <45242072+insertm...@users.noreply.github.com>
AuthorDate: Tue Nov 18 16:41:26 2025 +0100

    [Web] Fix progress reporting when loading from cache (#18450)
    
    ## Problem
    
    When loading model shards from cache (not network), the progress
    indicator
    always showed 0% because `fetchedBytes` was not incremented during the
    cache
    loading phase in `fetchTensorCacheInternal()`.
    
    The `reportCallback` function calculates progress as `fetchedBytes * 100
    / totalBytes`,
    but `fetchedBytes` was only updated during the network download phase
    (line 1361),
    not during the cache loading phase (lines 1377-1427). This caused the
    progress
    to remain at 0% until completion when loading from cache.
    
    ## Solution
    
    This fix increments `fetchedBytes` and updates `timeElapsed` after
    processing
    each cached shard (matching the behavior of the network download phase).
    The
    progress callback now correctly reports:
    - Percentage completed (`fetchedBytes * 100 / totalBytes`)
    - MB loaded
    - Time elapsed
    
    ## Changes
    
    - Added `fetchedBytes += shard.nbytes;` after processing each cache
    shard
    - Added `timeElapsed` update to ensure accurate time reporting
    - Matches the pattern used in the download phase (lines 1360-1361)
---
 web/src/runtime.ts | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/web/src/runtime.ts b/web/src/runtime.ts
index 8143f970ed..41bc43b54c 100644
--- a/web/src/runtime.ts
+++ b/web/src/runtime.ts
@@ -1359,7 +1359,7 @@ export class Instance implements Disposable {
         }
         timeElapsed = Math.ceil((perf.now() - tstart) / 1000);
         fetchedBytes += shard.nbytes;
-        reportCallback(fetchedShards++, /*loading=*/false);
+        reportCallback(++fetchedShards, /*loading=*/false);
       }
     }
     // We launch 4 parallel for loops to limit the max concurrency to 4 
download
@@ -1373,6 +1373,10 @@ export class Instance implements Disposable {
       ]);
     }
 
+    // Reset for the loading phase to avoid double counting with download phase
+    fetchedBytes = 0;
+    fetchedShards = 0;
+
     // Then iteratively, load the shard from cache
     for (let i = 0; i < list.length; ++i) {
       const shard = list[i];
@@ -1421,7 +1425,9 @@ export class Instance implements Disposable {
           throw err;
         }
       }
-      reportCallback(i + 1, /*loading=*/true);
+      fetchedBytes += shard.nbytes;
+      timeElapsed = Math.ceil((perf.now() - tstart) / 1000);
+      reportCallback(++fetchedShards, /*loading=*/true);
     }
   }